Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only mark it as a non-read-only, destructive, idempotent write; the description adds the substantive behavior: the zip is written to the output folder, the tool returns path and size rather than contents because files are large, Deere prepares the file asynchronously, and the result carries status 'preparing' vs 'saved' with retry_after_seconds. That is exactly the context an agent needs to avoid mis-handling the response. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and result, then the async caveat. Mostly tight, though the retry explanation is slightly repetitive ('call the tool again after retry_after_seconds' restates the status semantics).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Complete for a mutation-style download tool: it covers the source of the ID, output location, absent return contents (despite an output schema), and the asynchronous preparation contract. Nothing an agent needs to invoke and interpret it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so filename/resolution/shape_type defaults are already documented. The description still adds real semantics: where operation_id comes from (jd_list_field_operations), and how max_wait_seconds interacts with the 'preparing' status and retry_after_seconds, which the schema only describes as a timeout.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource+scope: downloads the point-by-point shapefile for ONE field operation and saves it to disk. It also clarifies the payload format (zip of ESRI shapefiles with yield/rate/moisture), which separates it from generic export siblings like jd_export_field_operations and jd_save_file.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear entry condition: operation IDs come from jd_list_field_operations, and only operations with shapefile_available=true have one. It also explains the retry path when status is 'preparing'. It does not explicitly say when to prefer this over jd_export_field_operations, which is the only remaining gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the file-writing nature is partly covered. The description goes further by describing the file's contents (org_id, field_id, seasons map), the return payload (file path plus per-season counts, not the operations), and the truncated_seasons caveat when the page cap is hit. That is substantial added disclosure, though it does not address what happens to an existing file at the same filename.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and scope, then usage, then output shape and truncation. Each sentence carries useful information, though it runs a bit long across five sentences for a tool this simple.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers the scoping, the alternative sibling, ID sources, the file layout, the returned summary (path and counts), and the truncation edge case. Even with an output schema present, the explanation of what the file contains and what is NOT returned is exactly what an agent needs to avoid mis-using the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so org_id, field_id, seasons and filename are already documented in the schema, including the filename default. The description adds only the ID provenance and a sample seasons list, which the schema already implies. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource+scope: saving all field operations for one field across multiple seasons to a JSON file. It explicitly distinguishes itself from jd_list_field_operations, which reads a single season, so an agent can separate the two without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit when-to-use ('multi-season history ... instead of reading each season into the conversation') and an explicit alternative ('use jd_list_field_operations to read a single season directly'), plus points to jd_list_organizations and jd_list_fields for the required IDs. Nothing about selection is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint and openWorldHint, and the description goes well beyond them: it constrains hosts and method, and details return shapes for JSON (lists wrapped as {"data": [...]}), images, and other text (truncated at 20,000 characters). It even documents the accept header needed to fetch a measurement map image.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core purpose in the first sentence, then layers routing guidance and return-format details. Every sentence conveys actionable information with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description carries the burden and does so thoroughly by describing JSON, list, image, and text/truncation return formats. An agent has everything needed to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% so both parameters are already documented as a baseline of 3. The description adds value by explaining that `url` can be an absolute Deere URL or a path joined to the configured base, and by giving the concrete accept value for image retrieval.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: a read-only GET request to any John Deere API endpoint. It explicitly distinguishes itself from siblings by saying to use it for Deere endpoints that no dedicated tool covers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use (endpoints not covered by dedicated tools) and how to use it: follow `links[].uri` values from other results and take IDs from the list tools. It also states hard constraints (only Deere hosts, only GET is ever sent), leaving nothing to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds that the response is the complete Deere record and that `embed` can pull in extra data, but says nothing about rate limits, error behavior, or record size. Useful but modest context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short paragraphs, front-loaded with the core action, and both the embed behavior and the id caveat earn their space. Minor redundancy between 'full record' and 'Returns everything Deere has,' but nothing wasteful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description needn't enumerate return fields, and annotations cover the read-only/open-world profile. The identifier routing note closes the main correctness risk. Remaining gaps (pagination, embed combination semantics) are minor.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, and the description legitimately adds a disambiguation the schema does not: the warning that `principalId` is a different identifier reserved for jd_get_machine_* tools. It also frames `embed` as the source of supplemental data in the returned record.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ('Get the full record for one machine or implement') and explicitly contrasts itself with siblings: jd_list_equipment is the source of the id, and jd_get_machine_* tools use principalId instead. An agent can route between these families without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the retrieval context (full record for a single piece of equipment) and, more importantly, which identifier to use and which tool family handles the other identifier. There is no explicit 'when not to use' or list of alternatives beyond the principalId routing note, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=true), but the description adds a genuinely useful behavioral detail: the boundary may be null when absent, or an embedded {"error": ...} object when the fetch fails, meaning partial failure is returned in-band rather than raised. That is context the annotations do not provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded first sentence delivers the core purpose, followed by return-shape detail and parameter provenance. Slightly padded by restating the schema-documented ID sources, but every sentence is relevant and nothing is buried.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description need not explain return values, yet it usefully flags the null and error-shaped boundary cases. For a two-param read tool with full schema coverage, this is essentially complete; only minor guidance on sibling selection is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both parameters already carry descriptions naming their source tools, so the description's restatement of provenance is largely redundant. Baseline 3 is appropriate since the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (get), a singular resource (one field), and the exact scope of what comes back (field record plus its active boundary). This clearly distinguishes it from jd_list_fields, which returns many fields without boundary geometry.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly tells the agent where to source both required IDs (org_id from jd_list_organizations, field_id from jd_list_fields), which establishes a clear call ordering. It stops short of naming exclusions, e.g. when to prefer jd_list_fields or jd_get_field_operation_measurements, so it is not a full 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnlyHint, openWorldHint), and the description adds genuine behavioral detail beyond them: the branching return shape (a `measurements` collection vs. a single measurement object when measurement_type is given) and the categories of data returned. It does not discuss pagination or limits, but the output schema partly covers structure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then return shape, then the parameter provenance. Three sentences, each carrying weight, with only mild redundancy between the description and the param descriptions for operation_id.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description need not explain return formatting, yet it still conveys the conditional shape and data categories. Combined with readOnly/openWorld annotations, the agent has enough to invoke correctly; only cross-tool alternatives remain unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: it tells the agent the operation_id's provenance and that a valid measurement_type value (e.g. HarvestYield) is discoverable by calling without the parameter ('as listed by this tool'). That discovery hint goes beyond the schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Get the measurement totals of one field operation') and names the exact fields returned (area, material, rate totals and averages, yield). It is clearly distinguishable from siblings like jd_list_field_operations, which it references only as the source of the operation_id.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent on how to obtain operation_id ('comes from the id of an item returned by jd_list_field_operations') and explains the measurement_type conditional (omit to list every type). However, it does not name an alternative tool for the case where the agent might want measurements another way, so it stops short of full when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds the embed_shapes conditional-return behavior, but that same behavior is already documented in the schema's embed_shapes param, so the net new behavioral insight is modest.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core action is front-loaded in the first sentence, followed by the conditional return note and the ID-sourcing guidance. Three short sentences with little waste, though the ID-sourcing line is somewhat repetitive with the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the return values need not be explained, and the description covers the embed_shapes toggle and full param-sourcing chain. Adequate for a single-record read tool with full schema coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description restates the source of each ID, which duplicates the schema param descriptions rather than adding format or syntax detail beyond them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb (get) and resource (one guidance line on a field), with 'one' implicitly contrasting with the jd_list_guidance_lines sibling. It is clear what the tool retrieves, though it never names the list sibling explicitly to sharpen the distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides a concrete prerequisite chain, telling the agent exactly where to obtain org_id (jd_list_organizations), field_id (jd_list_fields) and guidance_line_id (jd_list_guidance_lines). It stops short of stating when to prefer this over jd_list_guidance_lines or any exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=true), so the bar is lower. The description adds real value beyond them: it discloses the return key ('alerts') and the hard 7-day span constraint imposed by Deere plus the recommended workaround, which an agent could not infer from the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with purpose, then provenance, then the operational constraint. No filler; the awkward indentation is cosmetic rather than wasteful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be spelled out, and the description still names the payload key. Provenance of the required ID and the request-window constraint are both covered, so an agent has everything needed to call this correctly for a 4-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all four parameters, including principal_id's provenance and the ISO 8601 format for the dates. The description only restates principal_id's origin and relates the 7-day constraint to the date range, adding marginal meaning beyond structured data. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Starts with a specific verb+resource ('Get machine alerts') and immediately disambiguates the term with '(diagnostic trouble codes) for one machine'. An agent can distinguish this from the equipment-related siblings (jd_list_equipment, jd_get_machine_engine_hours, etc.) without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear operational context: principal_id is sourced from jd_list_equipment, and the 7-day window rule tells the agent when to split requests. It stops short of explicitly naming an alternative tool or stating when NOT to use this one, so it doesn't reach a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety behavior is covered. The description adds that reports are returned under 'device_state_reports', which is modest extra context; it says nothing about pagination, rate limits, or what happens when a window contains no reports.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Tight and front-loaded: purpose first, then return location, then parameter guidance. The 'Returns the reports under device_state_reports' sentence is somewhat redundant given an output schema exists, so slightly less than perfectly economical.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read tool with full schema coverage and an output schema, the description covers purpose, ID sourcing, and the two mutually exclusive query modes. Missing only edge-case behavior (empty windows, default when neither last_known nor dates are given).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters are already documented with formats in the schema — baseline 3. The description adds the provenance of principal_id and the last_known vs date-window tradeoff, which is a small increment over the schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Get device state (terminal status) reports for one machine,' with a scope qualifier that separates it from sibling read tools like jd_get_machine_alerts or jd_get_machine_engine_hours. It does not explicitly name those siblings, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives actionable routing: `principal_id` comes from jd_list_equipment, and 'Use last_known=True for the latest report, or a start_date/end_date window for history.' This tells the agent which mode to pick but offers no when-not-to-use guidance or alternative-tool routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds value beyond that by disclosing the cross-tool dependency on jd_list_equipment for principal_id and by stating which key the readings are returned under, letting the agent plan a two-call flow.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, zero filler, and front-loaded: purpose first, then return shape, then parameter source, then mode selection. Each sentence carries distinct information an agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and full schema description coverage, the description needs only to add dependencies and mode semantics, which it does. It is nearly complete; pagination or result-size limits for a date-range history query are the only unaddressed concern.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description goes further by explaining how last_known relates to the start_date/end_date window (mutually exclusive modes) — semantics the schema presents only as three independent optional fields. It adds real meaning on top of the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Get engine hour readings for one machine') and names the returned payload key, so the agent knows exactly what comes back. It does not explicitly differentiate itself from the adjacent sibling jd_get_machine_hours_of_operation, which is the one name an agent could plausibly confuse it with.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives usable mode-selection guidance: last_known=True for the current total versus a start_date/end_date window for history, plus the provenance of principal_id. It stops short of any when-not-to-use or explicit sibling routing, which is the only gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds real value beyond that by disclosing that detailed_state and summarize_duration are passed through to Deere unchanged (implying upstream validation and Deere-specific semantics) and that results land under 'hours_of_operation'.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose in the first sentence, followed by return container, ID provenance, and date/filter behavior. No filler sentences, though the provenance and date-window sentences could be tightened slightly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the description still names the 'hours_of_operation' container. Combined with the annotations and full schema coverage, an agent has enough to invoke it correctly; only explicit routing against sibling machine-hour tools is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter is already documented in the schema with format details (ISO 8601 UTC examples, principalId/passthrough notes). The description largely repeats that; the cross-tool ID provenance is helpful but already present in the schema text, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Get) and resource (machine hours of operation) and concretely defines the measurement as time spent working, idle, or transporting over a period. This distinguishes it from sibling reads like jd_get_machine_engine_hours and jd_get_machine_alerts without the agent needing to open another schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear operational context: principal_id is sourced from jd_list_equipment and org_id from jd_list_organizations, and start_date/end_date bound the period. It does not explicitly say when to prefer this over engine-hours or other machine reads, so it stops short of full when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds real behavioral context beyond that: results arrive under a 'locations' key, Deere enforces a maximum 1-month span per request, and principal_id must be sourced from jd_list_equipment. No auth or pagination detail, and nothing contradicts the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the purpose, then return shape, then prerequisites, then the alternative mode. Every clause carries information; no filler or restatement of the name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described in depth, and the description still notes the 'locations' container. Combined with complete parameter docs and an explicit range limit and dependency, an agent has everything needed to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all four parameters are already documented with formats and defaults (ISO 8601 UTC, last_known semantics). The description still adds cross-tool provenance for principal_id and the relational constraint between start_date and end_date, which the schema does not express.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource with clear scope: 'Get GPS location points for one machine.' An agent immediately knows this is telemetry history, not alerts or engine hours. However, it never names a sibling tool it should be chosen over, so it stops short of full sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete usage direction: 'For where the machine is now, prefer last_known=True instead of pulling history,' and states the 1-month window constraint. It does not, though, route the agent between this tool and other machine-level tools such as jd_get_machine_device_state_reports.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds genuine behavioral context beyond that: it discloses the breadth of the payload (field, work type, status, instructions, operations and assignments), which is the key signal for choosing a heavyweight single-record fetch over a list call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short paragraphs, front-loaded with the verb+resource and followed immediately by payload scope and ID sourcing. No filler sentences; every clause adds routing or expectation-setting value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be explained, and the description covers purpose, payload breadth, and how to obtain both required IDs. It omits only edge behavior such as what happens for an unknown erid or cross-org access restrictions, which is a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema descriptions already state the provenance of both IDs ("from jd_list_work_plans", "from jd_list_organizations"), so the description's sourcing note is largely duplicative. Baseline 3 is correct when the schema carries parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Get the full record of one work plan") and scopes it to a single plan, which cleanly separates it from the sibling jd_list_work_plans. It also enumerates what the record contains, so an agent knows this is the detailed single-record counterpart to the list tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete prerequisite routing: get `org_id` from jd_list_organizations and `erid` from jd_list_work_plans, which tells the agent exactly how to reach a callable state. It stops short of stating when-not to use it (e.g. vs. the list tool for bulk retrieval), so it is clear context without explicit exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds meaningful behavior: the exact identifier mapping between tools and the fact that `embed` injects the full record under 'raw'. It stops short of describing pagination semantics, which item_limit hints at but doesn't fully explain.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in the first sentence, followed by return fields and ID semantics. It is dense but every sentence carries information relevant to correct invocation; the return-field list is slightly redundant given an output schema exists.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter list tool with full schema coverage, an output schema, and annotations, the description covers the essential cross-tool wiring an agent needs. Remaining gaps (paging behavior, default page size) are minor and partly covered by parameter descriptions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds genuine value by disambiguating `id` vs `principalId`/`principal_ids`, which are the most error-prone parameters in this tool and directly affect whether downstream calls succeed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List the machines and implements in an organization') and scopes it clearly. It is distinguishable from jd_get_equipment, which the description explicitly notes takes `id`, and from the jd_list_* siblings by resource.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives strong chaining guidance: org_id comes from jd_list_organizations, and it explains that principalId feeds the jd_get_machine_* tools while id feeds jd_get_equipment. This tells the agent how to route the outputs. It does not explicitly state when to prefer this list over a single-entity get, but the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations provide readOnlyHint/openWorldHint, and the description adds a real constraint beyond them: Deere limits the start_date/end_date filter to a 7-day window per request. It also discloses that shapefile availability is signaled via `shapefile_available`, which is useful behavioral context for downstream chaining.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the purpose, then usage, then constraints in a logical order. The long enumeration of return fields is somewhat verbose given an output schema already exists, but it is dense and non-repetitive rather than padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Because an output schema exists, explaining return values is not strictly necessary, yet the description covers the key shape and the 7-day constraint, making the call self-sufficient. Only minor gap is no explicit guidance on the alternative export/measurement tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds cross-parameter meaning the schema lacks: the date window is capped at 7 days, one crop season per call is the norm, and org_id/field_id provenance is spelled out. That is real added value over the field-level descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('List the field operations recorded on one field') and enumerates the operation kinds covered (tillage, seeding, application, harvest). The mention that each operation's `id` feeds jd_get_field_operation_measurements and the shapefile download cleanly separates it from those siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear operational context: 'One crop season per call is the normal use', and points to jd_list_organizations and jd_list_fields for the required IDs. It does not, however, state when to prefer this over jd_export_field_operations or when a single-operation lookup (jd_get_field_operation_measurements) is the better call.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds genuinely useful beyond-annotation context: the identity of the returned id and the downstream tools that consume it. It is silent on pagination or whether archived fields are included by default, which keeps it out of the top band.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in one short sentence, followed by return shape and id linkage; every sentence carries information. The return-field enumeration is slightly redundant given an output schema exists, but it is brief.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose, prerequisite, return shape, and cross-tool id semantics, and the output schema handles detailed return structure. Only gaps are pagination/result-size behavior for an organization that may hold many fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for the single `org_id` parameter, so the schema already carries the semantics and baseline 3 applies. The description repeats the same sourcing hint ('from jd_list_organizations') without adding format, validation, or failure behavior.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource with scope ('List the fields in one organization'), and positions itself in the tool graph by explaining that the returned `id` is the `field_id` consumed by jd_get_field, jd_list_field_operations, jd_list_guidance_lines and jd_list_work_plans. An agent can distinguish this list tool from the single-field getter without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives the prerequisite for the only parameter (get `org_id` from jd_list_organizations), which is clear context for use. It does not state when to prefer this over jd_get_field (single field) or explain exclusions, so it stops short of explicit when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare read-only/open-world, so the description carries the rest and does so well: it names the returned fields, explains that embed_shapes adds a full record with geometry under `raw`, and warns that this makes responses larger. It does not mention pagination or result limits, which is the main remaining gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose in the first sentence, then return shape, then input provenance. Every sentence is functional. Slightly verbose in restating the returned field list, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter list tool with an output schema and full schema coverage, the description covers the essentials: scope, parameter provenance, the sibling to use for single-item fetches, and the opt-in shape embedding. Pagination behavior is the only notable omission, and the output schema may already carry that.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema lacks — that embed_shapes nests the complete record including geometry under a `raw` key on each item. It says nothing about `status` or `record_filter` beyond what the schema already documents ('Omit for Deere's default').

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource with explicit scope: 'List the guidance lines stored on one field.' The scope qualifier ('on one field') and the closing note that a line's `id` is the `guidance_line_id` used by jd_get_guidance_line cleanly separate this collection tool from its singular sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It tells the agent exactly where the two required inputs come from (org_id from jd_list_organizations, field_id from jd_list_fields) and explicitly routes to jd_get_guidance_line for single-record retrieval. There is no explicit when-not-to-use statement, but the list-vs-get split is unambiguous from the chaining note.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safe-read profile is covered. The description adds the upstream dependency for org_id, but return details it lists are already available via the output schema, so added behavioral value is modest.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action, followed by compact supporting notes. Every sentence is short and purposeful, though enumerating return fields overlaps with the output schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter read-only list tool with a full output schema, the description is complete enough: it states the action, the key dependency, and where org_id comes from. Return values need not be explained further given the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both parameters are fully documented in the schema (org_id source and record_filter semantics with default). The description reinforces the org_id origin but adds no syntax or meaning beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (List) with a specific resource (machine operators) and scope (defined in an organization), which an agent can immediately understand. The resource is distinct from all siblings (organizations, fields, products, work plans), so no sibling disambiguation is needed, but the description does not explicitly contrast with alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides one concrete prerequisite: 'Get org_id from jd_list_organizations.' This is useful context, but there is no guidance on when to use this tool versus alternatives, nor any exclusions or conditions for the record_filter behavior beyond what the schema already states.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial context beyond them — that unconnected organizations yield empty data or 403, and that manage_connections_url appears only in that case. This is exactly the behavioral detail (auth/permission failure mode) an agent needs before calling downstream tools.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads what it lists, then the response fields, then the routing guidance, then the failure-mode caveat. Four tight sentences, each carrying distinct information with no repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Though an output schema exists (so field definitions are not strictly required), the description still supplies the semantic interpretation of `connected` and the 403/approval flow. Nothing an agent needs to select or correctly invoke this tool is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Zero parameters, so the baseline is 4; the schema is trivially complete. The description instead documents the response shape (id, name, type, member, connected), which is useful but is return-value rather than parameter information.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List the ... organizations this sign-in can access') and scopes it to the authenticated sign-in's access, which no sibling covers. It also positions itself as the entry point ('Start here'), clearly distinguishing it from the jd_list_*/jd_get_* siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says to start here and explains why: the organization `id` is the `org_id` every other tool needs. It also gives the concrete follow-up condition for the `connected: false` case (open manage_connections_url and approve access), so the agent knows both when to use this tool and what to do next.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=true), so the bar is lower. The description still adds genuinely useful behavior beyond that: one call returns only one product_type, the returned field set is enumerated, and it tells the agent where org_id must come from.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action in the first sentence, then scope, then provenance. Slightly wasteful: it enumerates return fields even though an output schema exists, which is redundant real estate.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema exists and 100% parameter coverage in the schema, the description needs only the action, the one-type-per-call constraint and org_id provenance — all present. Minor gap: nothing notes pagination or result-size behavior for large organizations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3 by rule. The description restates the five product_type kinds in prose (mapping to the enum) and the org_id provenance, but adds no syntax or format detail the schema does not already carry.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('List one kind of product defined in an organization') and immediately constrains scope to a single product_type per call, enumerating the five kinds. An agent can distinguish this from jd_list_fields, jd_list_operators, etc., without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context: use it to see what an organization has defined, e.g. which seed varieties or chemicals exist, and directs the agent to jd_list_organizations for org_id. No explicit when-not or alternative tool for product discovery is named, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds real workflow context by naming the parent lookup (jd_list_organizations) and the downstream consumer (jd_get_work_plan), though it says nothing about pagination or result limits for a potentially large list.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action, then the handoff note. The enumerated return fields are somewhat redundant given an output schema exists, but the rest is tight and waste-free.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description needn't explain returns, yet it does name the key fields when passing erid downstream. Combined with the org_id sourcing instruction, an agent has everything needed to call this correctly in sequence.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and each parameter already carries its own description (e.g., 'Omit for all years', 'Omit for Deere's default'). The description only restates the filter axes ('optionally for a year, kind of work or fields') without adding format or semantic detail, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List the work plans of an organization') plus the filter dimensions, and explicitly distinguishes itself from the sibling read tool jd_get_work_plan by naming the erid handoff. An agent can tell it apart from jd_get_work_plan without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context: get org_id from jd_list_organizations, and use the returned erid with jd_get_work_plan. It does not state when NOT to use it (e.g., retrieving a single plan's detail), but the chaining guidance makes the intended workflow unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds behavior beyond the annotations: path sandboxing (filenames outside DEERE_OUTPUT_DIR are refused) and overwrite semantics (an existing file with the same name is replaced). This usefully corroborates the destructiveHint=true annotation rather than merely repeating it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the purpose, then usage condition, then constraints and return behavior in a tight sequence. Every sentence carries information; only the return-value sentence is arguably redundant given the output schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter write tool with full schema coverage and an output schema, the description covers what matters: scope, safety constraint, overwrite behavior, and return shape. Nothing required to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters are already fully documented with examples and relative-path support. The description adds no format or constraint detail beyond what the schema provides, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (save) and resource (text content written to a file), plus concrete content types like CSV or summaries. It is easily distinguishable from every sibling, which are all read/query tools, though it does not explicitly name one.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear triggering condition: 'Use this when the user wants a result kept on their computer.' It also states the operating constraint (writes confined to DEERE_OUTPUT_DIR). No explicit exclusion or named alternative, but for a singleton write tool that context is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.