Cairn

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety and determinism profile is covered. The description adds the temporal scope ('since 2016') and the data sources used, which is useful context, but says nothing about rate limits or response size.

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?

A single dense sentence that front-loads the purpose and then enumerates outputs. It is efficient, though the long mid-sentence list of metrics makes it slightly harder to scan than a split structure would be.

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-parameter read-only lookup with full schema coverage and no output schema, the description tells the agent exactly what headline metrics come back and the time window, which compensates for the absent output schema. Minor gaps remain around result size and usage routing.

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%; the schema already documents the 'section' parameter format and that paragraph references are accepted. The description only names example sections, adding no syntax detail beyond the schema. 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 precise verb+resource: 'Headline enforcement figures for one 29 CFR section.' It enumerates exactly what is returned (citations, inspections, penalties, median penalty, rank, interpretation-letter counts) and names example sections, making it easy to distinguish from search_standards and top_cited_standards.

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 by 'for one 29 CFR section' – the agent infers this is a single-section lookup rather than a search. But it never states when to prefer this over search_standards or top_cited_standards, and gives 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 readOnly/idempotent/non-destructive, so the lower bar applies, and the description still adds substantive behavior: result cap of 10, a citation-count floor (at least 50 citations since 2016), most-cited-first ordering, and that results include headline figures plus a link. Only the vague phrase 'headline figures' leaves a small 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?

Two tightly packed sentences: the first states what it searches and how, the second states what comes back, its ranking, and its filter threshold. Nothing is redundant and the operative information is front-loaded.

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-only search with no output schema, the description covers the essentials an agent needs: query forms, result count, ranking rule, eligibility threshold, and presence of a link. The only soft spot is that 'headline figures' is not defined, leaving the exact result fields underspecified.

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 50% — the limit parameter has no schema description — but the description supplies the missing semantics ('returns up to 10') and enriches the query parameter with concrete format examples beyond the schema's generic wording. It adds real value over the structured fields, though it never explains limit's 1-10 range explicitly.

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 (find workplace safety standards) and clarifies the searchable surface (29 CFR section number or title words) with concrete examples. It is clear what the tool does, but it does not differentiate itself from the sibling top_cited_standards, which by the description's own ranking/timestamp behavior sounds nearly identical.

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 examples ("1910.14", "lockout", "fall protection", "forklift") make it clear how to phrase a query, which is useful implied guidance. However, there is no explicit statement of when to use this versus get_standard or top_cited_standards, and given the apparent overlap with the latter, that omission matters.

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 carry readOnly, idempotent, non-destructive and closed-world hints, so the safety profile is covered. The description adds real value beyond them: the ranking is capped at 10, the window is since 2016, and the universe of valid CFR parts is enumerated. It does not describe whether citation counts are returned.

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?

A single front-loaded sentence with the core purpose first, followed by the part enumeration. The long list of part codes reads as a run-on, but every element carries meaning and nothing 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 still conveys what comes back (a ranked list of the 10 most-cited standards), the scope filter, and the time window. Annotations cover safety traits. Only the return shape (does it include citation counts?) is left unstated, 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 only 50%; cfr_part has a description while limit has none. The description compensates by enumerating the valid part codes (1910, 1926, 1904, 1915, 1917, 1918, 1928), which the schema lacks entirely, and 'The 10 most-cited' explains the limit default/max. The limit parameter itself is still never discussed.

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 resource (29 CFR safety standards), a ranking criterion (most-cited), a fixed scope (top 10) and a time window (since 2016). It is clearly distinguishable from get_standard and search_standards by its ranked, aggregate nature, though it never names 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?

Usage is implied rather than stated: 'for all standards or one CFR part' tells the agent it can run unfiltered or scoped, but there is no explicit when-to-use guidance, no exclusions, and no pointer to search_standards or get_standard as alternatives.

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