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

Annotations already flag destructive, open-world, non-idempotent behavior. The description adds useful context that URLs are not accepted and that the target's gates and dry-run settings apply, but it does not explain the practical implications of the destructive hint or confirm/dry-run requirements.

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 two compact sentences with the core constraint front-loaded. There is little waste, though the phrase 'target's gates and dry-run apply' is vague and could be more actionable.

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?

This is a complex meta-tool with seven parameters, nested objects, destructive behavior, and no output schema. The description is too short to explain how to construct body/query/path_params, how confirm works for deletes, or how dry_run defaults affect writes. It leaves too much to be inferred from the 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 only 57%, and the description only elaborates on the route parameter's accepted forms. It does not explain body, query, path_params, confirm, or dry_run beyond what the schema already partially provides. The description fails to compensate for the undocumented parameters.

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 action (calling a mapped route) and two accepted identifiers (tool name or route id). It also clarifies that free-form URLs are rejected. It is clear but does not explicitly distinguish when to use this meta-tool versus calling a concrete sibling directly.

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 only usage constraint given is that free-form URLs are not accepted and that the target's gates/dry-run apply. There is no explicit guidance on when to use this tool instead of singleops_discover_tools or a concrete singleops_read_* tool. The schema mentions discover_tools, but the description itself does not route the agent.

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 establish that this is a safe, read-only, idempotent, closed-world operation. The description adds useful behavioral context by explaining grouping, filtering, enabled/disabled state, and the exact return shape.

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 compact and front-loaded: one sentence covers purpose and filters, and one sentence gives the return structure. There is no wasted text.

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 there is no output schema, the description appropriately supplies the JSON return shape. It covers filters and enabled state, though it could state default behavior when no filters 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 input schema already documents both parameters. The description reinforces that results can be filtered by domain and read/write, but it does not clarify the other enum values such as delete, denied, or meta beyond what is already in 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?

The description states a specific verb and resource: it lists every tool, grouped by domain, with filters. This clearly distinguishes the discovery/meta tool from the many sibling SingleOps API tools.

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 implied because this is a discovery tool, but the description does not explicitly say when to call it versus calling a specific sibling tool, nor does it state exclusions or recommended workflow.

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 safety (readOnly, idempotent, non-destructive, openWorld), so the description's job is to add scope and output context. It does: it discloses that only parameter-free GET routes are replayed and gives the return shape {probed, passed, failed, results[]} despite no output schema. Missing detail on what a 'failed' entry contains or whether probing hits live rate limits.

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?

One tightly packed sentence that front-loads the mechanism, then the purpose, then the return shape. Nothing is redundant and no filler is present.

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 single-optional-param diagnostic tool with no output schema, the description conveys mechanism, intent, and the top-level result envelope. It falls slightly short on what the per-route `results[]` entries or 'failed' classification mean, which an agent would need to interpret the diagnostic output.

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 optional `limit` parameter is already documented in the schema (max routes to probe, default 25). The description adds no extra semantics about what limiting routes means for coverage or result fidelity, 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 mechanism (replay parameter-free GET routes, diff response keys against a known map) and an explicit goal (detect SingleOps changing its internal API). This clearly distinguishes it from data-returning siblings like singleops_call_route and singleops_discover_tools, which fetch values rather than validate contracts.

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 stated goal ('to detect SingleOps changing its internal API') implies the usage context of a contract/regression check, but there is no explicit when-to-use, when-not-to-use, or named alternative. An agent must infer that this is not for retrieving data and that only parameter-free routes are covered.

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 readOnly, idempotent, open-world, and non-destructive behavior, so the safety profile is covered. The description contributes real extra context by disclosing that the definition was inferred from observed traffic and results should be confirmed, plus it lists the JSON response keys (draw, recordsTotal, data, meta, etc.) absent an output schema. It stops short of explaining pagination semantics or rate-limit/error behavior.

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 purpose and caveat are front-loaded, which is good, but the body is a 68-item enumeration of parameter names that duplicates the input schema verbatim and dominates the description. That bulk does not earn its place; a sentence on DataTables conventions would have been far more useful.

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 68-parameter tool with no output schema, listing the response keys and flagging the inferred/unverified nature are genuinely valuable. However, the description never explains how the paging/sorting/filter parameters are meant to be combined or what the report actually contains, so an agent still lacks the operational detail needed to call this confidently.

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 nominally 100%, so the baseline is 3, but those descriptions are placeholders ('Query parameter "draw"') that convey no meaning. The description merely mirrors the schema's parameter-name dump and never explains DataTables concepts like draw/start/length, search[value], or the table_filter_start/end range params, so it adds no true semantic value.

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 archived jobs report') and pins it to the concrete endpoint GET /reports/archived_jobs_report, so the agent knows exactly which report is fetched. It does not, however, distinguish this from the many sibling report tools (job_labor_report, job_expenses_report, etc.) beyond the name itself.

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 only guidance offered is 'Inferred from the SingleOps web app's own traffic; confirm results,' which is a reliability caveat rather than a when-to-use rule. Nothing says when this report is preferred over the other archived/jobs/report siblings or what filters are needed to get meaningful output.

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, idempotentHint, destructiveHint=false, and openWorldHint, so safety is covered. The description adds one genuinely useful behavioral fact: the parameters were reverse-engineered from observed traffic and results should be verified. It also lists return keys, but says nothing about pagination defaults or how the DataTables params affect output.

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 middle of the description is a 90-name enumeration of columns[0..11] params that duplicates the schema verbatim and pushes the two actually useful sentences (the inference caveat and the return keys) into the background. Structure is back-loaded and dominated by boilerplate.

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 94-parameter tool with no output schema, the description does at least name the return keys (draw, recordsTotal, recordsFiltered, data, meta, table_id, settings), which the schema does not cover. But it never says what data columns the report returns or what the key business filters do, leaving an agent unable to interpret or filter results with confidence.

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% but the per-parameter descriptions are tautological ('Query parameter "start"'), so the description could have added real meaning. Instead it mostly re-lists the same names; its only added value is making it apparent these are DataTables-style paging, sorting, and column-search params and flagging business filters like show_only_eligible_for_renewal, include_on_hold, and tag_ids. It does not explain what any of those filters do.

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 names the resource (batch renew jobs report) and the endpoint, but 'Get batch renew jobs report' largely restates the name and title. Among roughly 60 report siblings, nothing explains what this report contains or how it differs from, say, get_archived_jobs_report or search_jobs_report.

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 only guidance is the caveat 'Inferred from the SingleOps web app's own traffic; confirm results', which describes reliability rather than when to use the tool. There is no guidance on when to choose this report over the many sibling report tools, and no exclusions or prerequisites.

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, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds meaningful context by warning that the endpoint was inferred from observed traffic and results should be confirmed, and it lists the response keys. It still does not describe pagination behavior or reliability limits beyond the inference caveat.

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 purpose and endpoint are front-loaded, but the description then dumps a long raw list of DataTables query parameter names that largely restates the schema. That makes the definition unnecessarily bloated rather than concise.

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 complex 44-parameter report tool with no output schema, the description provides the endpoint, return keys, and an important inference caveat. However, it does not explain the semantics of the DataTables-style filters, the report contents, or how this report relates to sibling report tools, leaving real gaps for correct invocation.

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 even though the schema descriptions are generic placeholders. The description enumerates many query parameter names seen in traffic, but it does not explain their meaning or syntax beyond what the schema already exposes.

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: "Get client labor report," and identifies the backing endpoint GET /reports/client_labor. It is clear what the tool retrieves, though it does not explicitly differentiate it from sibling report tools such as singleops_read_get_job_labor_report.

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 gives no when-to-use guidance and does not mention alternatives or exclusions. The caution "Inferred from the SingleOps web app's own traffic; confirm results" is useful context but is not usage 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, idempotentHint and destructiveHint=false, so safety is covered. The description does add genuinely useful behavior context: the endpoint was reverse-engineered from observed traffic and results should be validated, and it names the response keys (draw, recordsTotal, recordsFiltered, data, meta, table_id, settings) despite no output schema. It does not disclose pagination defaults, size limits, or what 'select_years[]' controls.

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 content is front-loaded and useful, but roughly 90% of the text is a 100+ item enumeration of query parameter names copy-pasted from the schema. This bloats the description enormously while adding zero information, and buries the one valuable caveat about inferred traffic.

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 102 parameters, no output schema, and a warning that the endpoint is inferred, the description does supply return keys and a validation caveat, which are the right things to include. It still omits how to actually shape a call (which params matter, how filtering by year/client works) and how large responses are handled, so an agent must guess before invoking.

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?

Nominal schema coverage is 100%, but every schema description is a tautology ('Query parameter "start".'), so the schema conveys no semantics. The description merely re-lists the same parameter names verbatim without explaining DataTables conventions (draw as a request echo, start/length as pagination, columns[n][search][value] as per-column filters), leaving the agent no better off than the raw names.

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 first sentence names a specific verb and resource (get customer history report), so the intent is identifiable. However, nothing distinguishes it from the ~30 sibling report tools (customer type report, client labor report, payment totals report, etc.), so an agent cannot tell from the description which report answers which question.

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?

There is no statement of when to call this report versus alternatives, no prerequisites, and no note about what data it covers (years, clients, date range). The only guidance is a caution that results were 'inferred from the SingleOps web app's own traffic; confirm results', which is a reliability warning, not usage direction.

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 readOnly, idempotent, non-destructive, so the safety profile is covered. The description does add genuinely useful non-annotation context: the endpoint was "inferred from the SingleOps web app's own traffic" and results should be confirmed, which warns the agent the contract is unverified, and it lists the response keys. It stops short of saying what data the report actually returns.

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 and the useful caveat are front-loaded, but the bulk of the text is a comma-separated dump of ~44 query parameter names that the agent already receives verbatim in the schema at 100% coverage. That duplication dominates the description and pushes the one valuable sentence (traffic-inferred, confirm results) into the middle.

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 44-parameter tool with no output schema, the description does supply the return-key list and a caveat about reliability, which is more than nothing. However it leaves the agent without the essentials: which parameters are meaningful, typical pagination/date-range conventions, and what the report's rows represent.

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%, though the schema descriptions are pure tautologies ("Query parameter \"draw\""). The description merely echoes the same parameter names in a flat list and adds no semantics for what DataTables-style params (draw, start, length, columns[n][search][value]) or business filters (operation_ids, sales_rep_ids, table_filter_start/end) actually mean. High coverage makes 3 the correct 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?

The first sentence, "Get customer type report," simply restates the tool name and title with no added specificity about what the report contains (customer type breakdown of what — revenue, jobs, visits?). The endpoint path is the only concrete detail, and it does nothing to distinguish this from the ~30 sibling report tools in the same family.

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?

There is no guidance on when this report should be chosen over the many sibling reports (get_net_sales_report, get_customer_history_report, get_sales_rep_report, etc.), no prerequisites, and no mention of how to supply the date range or filters. "Confirm results" is a reliability caveat, not usage 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 readOnly, idempotent, openWorld, and non-destructive, so safety is covered. The description adds genuinely useful context beyond them: the parameters were reverse-engineered from observed traffic and results should be confirmed, and it names the JSON response keys (draw, recordsTotal, recordsFiltered, data, meta, table_id, settings).

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 dumps roughly 40 query parameter names verbatim, duplicating the input schema and pushing the genuinely useful information (traffic-inferred caveat, response keys) into a wall of noise. The signal-to-noise ratio is poor and the important caveat is buried mid-sentence.

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 53-parameter tool with no output schema, the description does supply the return keys, which helps. But it never explains how to practically drive the DataTables-style parameters or which subset matters for a typical report query, leaving an agent to guess among 53 optional params.

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%, but every property description is a trivial echo ('Query parameter "draw".'), and the description's long param list merely repeats those names without explaining DataTables semantics (draw/start/length, columns[N][search][value], order[0][dir]). Baseline 3 applies since the schema nominally documents all params, but no real meaning is added.

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 restates the tool name almost verbatim ('Get custom inputs report') and adds only the raw endpoint path. With 60+ sibling report tools, nothing distinguishes this report from get_sales_rep_report, get_items_report, etc., so an agent cannot tell what data it actually returns.

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 only guidance is 'Inferred from the SingleOps web app's own traffic; confirm results', which is a reliability caveat rather than usage guidance. There is no statement of when to choose this report over the many sibling reports or what prerequisites/filters are needed.

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, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new context: the route was inferred from observed traffic and results should be confirmed, which warns the agent the behavior may be approximate. It stops short of mentioning auth or pagination, so a 4 rather than a 5.

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 compact clauses: the purpose, the concrete endpoint, and the reliability caveat plus return keys. Everything is front-loaded and no sentence is 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?

With no output schema, the description compensates by enumerating the returned JSON keys (id, account_id, title, layouts, timestamps, user_id), which is enough for an agent to plan around the result. Combined with the read-only annotations, the definition is nearly complete; only auth and error behavior are absent.

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 id, extra_query and response_format, making 3 the baseline. The description adds nothing about parameter meaning beyond the implied record id, so it does not exceed that 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?

The description states a specific verb+resource ('Get dashboard by id') and pins it down with the concrete endpoint GET /api/v1/dashboards/{id}, so an agent knows exactly what resource is fetched. It does not explicitly differentiate itself from nearby siblings like singleops_read_list_widgets, 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?

There is no statement of when to use this over alternatives, no prerequisites, and no exclusions. The note 'Inferred from the SingleOps web app's own traffic; confirm results' is a reliability caveat, not usage guidance, so the agent is left to infer the call context.

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, idempotentHint, destructiveHint=false, and openWorldHint, so the safety profile is covered. The description adds useful context that the endpoint was inferred from app traffic and that results should be confirmed, plus the top-level return keys.

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 front-loads the purpose and endpoint well, but it then dumps dozens of raw query parameter names in a single run-on list. Much of that list is redundant with the schema and makes the description unnecessarily bloated.

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?

It provides the endpoint, a reliability caveat, a raw parameter list, and top-level JSON return keys, which helps because there is no output schema. However, for an 86-parameter report tool it does not explain report content, key filters, defaults, or the markdown/json response_format behavior.

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 lists the query parameters seen and the return keys, but it does not explain what the DataTables-style parameters mean or how key filters like table_filter_start and table_filter_end should be used.

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: 'Get equipment utilization report' and gives the endpoint path. It is clear what report is being fetched, though it does not explicitly distinguish this report from the many sibling report tools beyond the resource 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?

The only guidance is 'Inferred from the SingleOps web app's own traffic; confirm results,' which is a reliability caveat rather than when-to-use guidance. It does not name alternatives or explain when this report should be chosen over other report tools.

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 read-only, idempotent, non-destructive, and open-world behavior. The description adds useful provenance ("Inferred from the SingleOps web app's own traffic") and lists returned keys, but it does not explain report behavior, filtering semantics, or pagination beyond repeating parameter names.

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 opening sentence is concise and front-loaded, but the description then dumps a massive redundant list of fifty-plus query parameter names already present in the schema. That list is unreadable and does not earn 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?

For a complex 57-parameter endpoint with no output schema, the description does include the return keys, which is helpful. However, it does not explain the report's content, how the date filters should be used, or how the DataTables parameters interact, leaving significant gaps.

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 even though the schema descriptions are mostly tautological (e.g., "Query parameter draw"). The description merely repeats the same parameter names in a comma-separated list and adds no meaning about filters like table_filter_start/end or the DataTables-style parameters.

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 ("Get global planner report") and names the backing endpoint (GET /reports/global_planner). It does not distinguish this report from the many sibling report tools or explain what the report contains.

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?

There is no guidance on when to use this report versus alternatives such as get_dashboard, list_widgets, or the other report tools. The only guidance-like remark is the caveat "confirm results," which is about reliability rather than tool selection.

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 genuine value beyond the annotations: it discloses that the route was inferred from observed web traffic ("confirm results"), that the query is read-only despite using POST, and the success envelope {ok, status, redirect, id}. The parenthetical "(the new/updated record id)" is boilerplate residue implying a mutation, which is at odds with readOnlyHint=true, though the explicit "Read-only query sent as POST" sentence makes the intent clear.

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 clause, followed by endpoint, confidence caveat, field list, and return shape in tight succession. No sentence is decorative; even the caveat about inferred traffic earns its place by setting expectations for verification.

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 no output schema, the description supplies a return envelope and error behavior, which covers the main gap. Remaining unknowns (report columns, date format, pagination) are minor for a read-only report call whose safety profile is fully declared by 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?

Schema coverage is 100%, but the body is a free-form object with only additionalProperties, so the description's listing of start_date/end_date and the nested-object convention with a concrete example materially extend the schema. Date format and pagination/limit parameters remain unspecified.

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 inventory transactions report") and even names the underlying endpoint POST /reports/inventory_transactions. It does not differentiate itself from closely-named report siblings such as singleops_read_get_tree_inventory_report or singleops_read_get_items_report, so an agent must infer the boundary.

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?

There is no when-to-use / when-not-to-use guidance and no named alternative among the ~70 sibling report tools. The only procedural guidance concerns how to shape the body, not when this tool is the right choice.

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, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds a meaningful caveat that the endpoint was inferred from observed traffic and results should be confirmed — useful context beyond annotations — but it says nothing about pagination, rate limits, or result shape beyond listing keys.

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 purpose and caveat are front-loaded, which is good, but the description then dumps a massive 55-item parameter list that merely duplicates the schema keys, bloating the text without adding information. That enumeration does not earn its space.

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 55-parameter report tool with no output schema, the description does list the return keys (draw, recordsTotal, recordsFiltered, data, meta, table_id, settings), which partially substitutes for an output schema. But it leaves the meaning of the many filter/column parameters and the actual report content unexplained, so an agent cannot construct a meaningful call beyond guessing.

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 nominally 100%, but every property description is a tautology ('Query parameter "draw".'), so the schema provides no real semantic value. The description only enumerates parameter names with no explanation of meaning, format, or which are important, leaving effective semantic coverage low despite the reported number.

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 item groups report') and cites the underlying endpoint GET /reports/item_groups_report. However, it does not distinguish this report from close siblings like singleops_read_list_item_groups or singleops_read_get_items_report, so an agent cannot easily tell which one applies from the text alone.

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?

There is no explicit when-to-use, when-not-to-use, or alternative recommendation. The only caveat is 'Inferred from the SingleOps web app's own traffic; confirm results,' which is a reliability warning rather than routing guidance.

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