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

No annotations are provided, so the description carries the full behavioral burden. It does disclose the error case ('raises if no output carries that id') and that the response echoes the deleted object with deleted=True, but for a destructive operation it says nothing about irreversibility, permissions, or whether deletion is soft or hard.

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 short sentences, front-loaded with the action and scope, then return behavior, then id discovery, then the failure case. No filler and nothing 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?

An output schema exists, so the return-value sentence is supplementary rather than required, and the id source and error behavior are covered. The remaining gap is behavioral: nothing tells the agent whether a delete is recoverable, which matters for an irreversible mutation with no annotations.

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?

Only one parameter exists and schema description coverage is 100%, with the schema already noting the id comes from list_outputs_tool. The description repeats that source but adds no new syntax, format, or range meaning, 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 (delete) and resource (saved report output) with explicit scope ('one ... by id'), which cleanly separates it from the bulk-deleting sibling prune_outputs_tool. It also names list_outputs_tool as the id source, so an agent can distinguish it from the get/save output tools without opening a 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: ids come from list_outputs_tool, and the tool deletes exactly one output. However it never states when to prefer this over the sibling prune_outputs_tool, nor any prerequisite or exclusion, so the alternative-selection guidance is incomplete.

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?

readOnlyHint=true already tells the agent this is a safe read. The description adds genuinely useful behavior: default returns the most recent output, and gathered_date scopes to a specific day. It stops short of describing error behavior when no output exists or pagination/format details, but with annotations covering the safety profile this is adequate.

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 sentences, front-loaded with the core action and then the retrieval-mode distinction. No filler, though 'for compiling a report' is slightly redundant with the noun 'report output'.

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 both parameters are fully documented in the schema. The only gap is guidance on alternatives among the many sibling output/report 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% and both parameters carry their own descriptions, including the YYYY-MM-DD format hint. The description restates the date-filtering semantics but adds no syntax or edge-case meaning beyond the schema, 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 (read) and resource (gathered report output) clearly, and the report-definition name parameter anchors it. It distinguishes reasonably from save_output_tool and list_outputs_tool, though it doesn't explicitly name siblings or contrast scope.

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?

The description implies usage ('for compiling a report') and clarifies default vs. date-specific retrieval, but never says when to pick this over list_outputs_tool or get_spec_tool. No exclusions or prerequisites are given.

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, so safety is covered. The description contributes useful context that the payload is a prompt plus source config consumed by an automated gatherer on callback, but says nothing about staleness, permissions, or failure behavior for a missing report name.

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 tight sentences with the primary action front-loaded and no filler; every clause (what is returned, who calls it and when) earns its place.

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 explains the tool's role in the callback workflow. It is nearly complete for a one-param read tool, with only the lack of sibling differentiation as a residual 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 description coverage is 100% and the single 'name' parameter is documented with an example, so the schema carries the burden. The description only reinforces that the spec is keyed by the named report, adding no format or naming-convention detail beyond 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 ('Return the gather spec') and unpacks the return value into its two components (prompt + source config), which is more than the name conveys. It does not explicitly differentiate itself from lookalike getters such as get_sweep_tool or get_output_tool, so it falls 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?

The second sentence gives a real usage context: it is what the autonomous gatherer calls on callback for a named report. However, it offers no when-not guidance and never contrasts itself with the sibling getters, leaving the agent to infer the boundary.

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, so the description usefully adds that sweeps are pre-gathered before the gatherer runs and that data is stored as sections of compact records, including what the index contains. It omits auth/permission needs and any rate or size caveats beyond the schema's page_size max.

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 action in the first sentence and follows with just enough mechanism and call-order detail. The gatherer/Metsuke framing is somewhat jargon-heavy but earns its place by explaining where the data comes from.

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 documented, yet the description still tells the agent what the index yields and how to page. Read-only, no required params, and 100% schema coverage make this nearly self-sufficient.

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 reinforces the section/index relationship and pagination flow, but the run_id-vs-report_name selection and page defaults are left to the schema, adding little beyond it.

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: read the pre-gathered sweep for a run. The concept is clearly distinct from the listed siblings (output/report/definition tools), though it never explicitly names an alternative to contrast against, so it falls just short of 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 concrete call-order guidance: call with no section to get the index, then page through each section needed. That is clear usage context, but there are no explicit when-not conditions or named alternatives for choosing between run_id and report_name.

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, so safety is covered. The description goes further by describing the shape of results (one lightweight row per gather: id, report_name, gathered_at, window, status, finding_count) and, importantly, that payloads are NOT returned, which explains why the call is cheap. It does not discuss limits/pagination behavior beyond 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 the core action and ordering, followed by the return shape and the routing alternatives. Every sentence earns its place 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?

Output schema exists so return fields need no full enumeration, and annotations cover the read-only profile. The description completes the picture by explaining payload omission and sibling routing, leaving nothing an agent needs to call 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 description coverage is 100%, with both limit and report_name fully documented including defaults and max. The description adds no parameter detail, so the schema does the heavy lifting — 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 (List) and resource (saved report outputs / run history) plus ordering (newest first). It clearly distinguishes itself from get_output_tool (single run) and delete/prune_outputs_tool (pruning), so an agent can route without opening schemas.

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 names the alternatives and the conditions that select them: use get_output_tool to pull one run's findings, delete_output_tool/prune_outputs_tool to prune. The browse-vs-fetch tradeoff is spelled out rather than implied.

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?

readOnlyHint=true already tells the agent this is a safe read. The description adds the returned field set, which is mildly useful, but discloses nothing about pagination, ordering, rate limits, or result size. With annotations covering the safety profile, a 3 is appropriate.

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 sentences, front-loaded with the core action and followed by the return detail. No filler sentences, though the return-field enumeration is somewhat 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 zero-parameter list tool with readOnlyHint and an output schema already present, the description covers what an agent needs to select and call it. The only minor gap is absent guidance on empty results or result-size behavior, which the output schema does not address.

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?

The tool takes zero parameters, so the schema baseline is 4. Description adds no param info because there is none to add, and that is correct here.

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 all report definitions in the catalog') and enumerates the returned fields. It is clearly distinguishable from siblings like list_outputs_tool or get_spec_tool, though it never explicitly names that 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?

The scoping phrase 'all report definitions in the catalog' implies a browse/list use case, but there is no explicit when-to-use, when-not-to-use, or alternative routing guidance versus siblings such as list_outputs_tool or get_spec_tool.

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?

With no annotations, the description carries the full behavioral burden. It discloses that outputs are deleted, that keep_last=0 deletes all, and that it returns count and ids, but it does not state whether deletion is irreversible or what permissions are required.

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 description is short and front-loaded: purpose and return value first, then criterion semantics. Every sentence adds useful information without 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?

The schema fully documents parameters, an output schema exists, and the description explains the pruning criteria and return summary. The main remaining gap is behavioral safety context such as irreversibility and permissions, which matters because no annotations are provided.

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 important meaning beyond the schema. It clarifies the exactly-one-criterion constraint and explains the special keep_last=0 case and the strict 'before' behavior of before_date.

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 and resource: bulk-prune a report's saved outputs. The word 'bulk' helps distinguish it from a single-output deletion tool, though it does not explicitly name delete_output_tool as the alternative.

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 clearly instructs that exactly one criterion must be given and explains how to choose between keep_last and before_date. It does not explicitly compare this tool with delete_output_tool or list_outputs_tool, but the usage 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?

No annotations are supplied, so the description carries the full behavioral burden, and it discharges most of it: it discloses run-completion semantics, the one-row-per-fire cardinality, and that Metsuke stamps a run identity even on ad-hoc saves. It does not cover failure behavior or what happens when run_id refers to an already-completed run.

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 primary effect (persist and complete the run), then the payload convention, then the run_id branch. Every sentence adds operational information; nothing is padding.

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 mutation tool with no annotations, the description covers the essentials, and an output schema exists so return values need no explanation. The main residual gap is error/edge-case behavior (invalid run_id, duplicate fires), which a writer would still want stated.

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, but the description adds real meaning: it explains where run_id comes from (the fire callback), what omitting it does, and that payload findings should each carry source_url so the compiler can cite 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?

States a specific verb and resource ('Persist a gathered report output') and adds the consequential nuance that it 'completes the run that opened it.' This distinguishes it from read-side siblings like get_output_tool and list_outputs_tool, which cannot complete a run.

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 covers the two invocation modes: pass run_id from the fire callback to complete an in-flight run, or omit it for an ad-hoc direct save. It also states the triggering context ('after sweeping the sources'). It stops short of naming sibling tools (e.g. upsert_definition_tool, get_output_tool) as alternatives.

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?

With no annotations, the description carries the full burden and does so well: it discloses the dispatch mechanism (POST to Trentina alert endpoint forwarded to the owning gatherer), required env config (TRENTINA_ALERT_URL + METSUKE_ALERT_TOKEN), and the pull-owner branch behavior (run opened and left for owner). These are real side-effect and prerequisite details beyond 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?

The core purpose is front-loaded in the first sentence and the follow-up detail (mechanism, prerequisites, pull-owner case) is genuinely useful rather than filler. Slightly dense but every clause earns its place.

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 covers purpose, prerequisites, and the alternate pull-owner execution path. 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 description coverage is 100% and the single 'name' param is already documented with an example, so the schema does the heavy lifting. The description adds no syntax or semantics beyond it, making 3 the appropriate baseline.

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 ('Fire a report gather') and the distinguishing condition ('right now, without waiting for its schedule'), which separates it from scheduling/spec/definition siblings like upsert_definition_tool and get_sweep_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?

The 'right now, without waiting for its schedule' clause clearly situates when to use it versus the normal scheduled path, and it states the configuration prerequisite. It stops short of naming a sibling alternative, so not 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?

With no annotations, the description carries the full disclosure burden. It does add real behavioral context beyond the schema: owner_agent is data not code (so gathering can be re-homed without a rebuild) and schedule is a live cron that the built-in scheduler acts on. It is silent on the mutation semantics that matter most for an upsert — whether an existing definition is merged or overwritten, and what a name collision does.

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 with the action front-loaded and no filler. The owner_agent rationale sentence is longer than strictly necessary but does earn its place by justifying the field's design.

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 no explanation, and the schema fully covers parameters. But for a 6-parameter mutation tool with zero annotations, the description omits the upsert contract: whether omitted optional fields (schedule=None, owner_agent="kagetora", timezone="UTC") reset existing values or are preserved on update.

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 six parameters, establishing a baseline of 3. The description adds nuance for owner_agent (re-homing without rebuild) and schedule (live cron, scheduler-driven), but says nothing about name, gather_prompt, or source_config beyond what the schema states.

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?

"Create or update a report definition" gives a specific verb pair and resource, which is unambiguous. However it never distinguishes the definition-level write from the sibling trigger_report_tool (which fires a report) or list_reports_tool, leaving that distinction to be inferred from the name.

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?

Usage is only implied by "Create or update" — the description never states when to reach for this tool versus trigger_report_tool (fire now) or the listing tools. The cron/scheduler sentence explains one field's behavior rather than routing the agent to this tool over an alternative.

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