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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered structurally. The description usefully discloses the return shape (section structure with IR/AMC/GM counts) and hints at rule enumeration, but says nothing about result limits (the max-150 cap lives only in the schema) or pagination. It adds some value without contradicting 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 compact sentences, leading with the action and following with usage. The 'Part-FCL Subpart H' example earns its place by concretizing the subpart-listing use case, though the parenthetical about counts could be trimmed.

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?

There is no output schema, so the description carries the burden of describing returns, and it does so adequately (structure plus IR/AMC/GM counts, listable rules). The only real gap is the undisclosed 150-rule listing cap, which an agent would only discover from the parameter 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 description coverage is 100%, with the book enum values and the section_contains filter fully documented in the schema. The description only reinforces this with an example ('SUBPART H'-style scoping), adding minimal meaning beyond the structured fields, so the baseline of 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?

The description gives a specific verb and resource ('Show the structure of a book'), plus what the output contains (sections with IR/AMC/GM counts). It does not explicitly name or contrast itself with the sibling tools (search_easa_rules, get_easa_rule, list_easa_sources), so the agent must infer the boundary, but the purpose itself is unambiguous.

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?

'Use it to orient yourself or to list every rule in one subpart' states two concrete uses with a worked example (Part-FCL Subpart H). No exclusions or explicit alternatives are given, so it falls short of a full when/when-not routing statement.

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=false, so safety is covered. The description adds real context: it returns metadata, a citation string, and related AMC/GM, and discloses the ambiguous-reference behavior (returns candidates instead of erroring) – a trait not in 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?

Two tightly packed sentences, front-loaded with the core outcome and followed by the edge-case behavior. No waste.

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 no output schema, the description covers what is returned (full text, metadata, citation, related items) and the ambiguity fallback. Minor gap: it doesn't mention max_chars truncation of the returned text, which is relevant given the 60k cap.

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 75%, so the schema already documents ref, book, and include_related. The description adds no parameter-level detail (e.g., ref format or max_chars truncation behavior) beyond what the schema provides, matching the baseline for high coverage.

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 (Return) and resource (full text of one EASA rule) with exact scope, and names the content types (IR, AMC, GM, CS). Clearly differentiable from siblings search_easa_rules (search) and browse_easa_toc (navigate).

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?

Implies the single-rule retrieval use case versus search tools, and notes the ambiguous-reference fallback that returns candidates. However, it doesn't explicitly name the alternative (search_easa_rules) for when the exact reference is unknown.

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, and openWorldHint=false, so the safety and determinism profile is covered. The description adds that results carry publication dates, but says nothing about pagination, ordering, or how many books are indexed, so it adds only modest context beyond 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?

A single sentence with no waste: the action and the returned data are front-loaded, and the trailing purpose clause earns its place by explaining why the date matters.

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 no output schema, the description adequately conveys what comes back (indexed books plus publication dates). It would be stronger if it stated the ordering or approximate result size, but what an agent needs to call it correctly is present.

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 there is nothing for the description to disambiguate; the baseline for a no-parameter tool is 4. The description correctly avoids inventing arguments that do not exist.

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 indexed Easy Access Rules books') plus the returned field (publication date), which is more than a restatement of the name. It does not explicitly distinguish itself from the siblings search_easa_rules, get_easa_rule, and browse_easa_toc, though the 'list indexed books' framing is naturally distinct from search/get/browse.

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 rationale 'so answers can state which revision they are based on' implies when to call it (to identify the revision behind an answer), which is useful implied usage. However, it names no alternatives and gives no explicit when-not guidance, so the agent must infer routing relative to the sibling 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 readOnlyHint, idempotentHint and closed-world behavior, so safety is covered. The description adds genuine value beyond them by disclosing the result shape ('ranked rules with reference, type, location and a matching snippet'), though it omits ranking behavior and the effect of the limit parameter.

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: purpose, return content, then the routing hint, front-loaded with no wasted words. Every sentence 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 no output schema, the description usefully summarizes the return fields, and the sibling routing covers the main follow-up action. Minor gaps remain: no mention of the default/limit on result count or how ranking works, which an agent might need to size queries 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 high (75%) and the schema itself documents book, content_type and gives concrete query examples, so parameter meaning largely comes from structured data. The description adds no parameter-level guidance (nothing on book scoping or the limit cap), 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 and resource ('Full-text search across EASA Easy Access Rules') and enumerates the returned fields (reference, type, location, matching snippet). It also names the sibling get_easa_rule as the different tool for full text, so an agent can distinguish it immediately.

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 to get_easa_rule when full text is needed, which is clear usage context. It does not state when *not* to search (e.g. when a known exact reference should go straight to the getter, or how it relates to browse_easa_toc), 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.