Measured Agents

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

The annotations already declare the tool as read-only, idempotent, non-destructive, and closed-world. The description adds useful return-content context about the checklist and verification block, but does not mention not-found behavior or any access constraints.

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 a single front-loaded sentence with no wasted wording. It communicates the lookup key and notable returned fields efficiently.

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 simple read-only retrieval tool with annotations covering safety characteristics, the description is nearly complete. The remaining gap is minor: it does not describe behavior when the slug is unknown or invalid.

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 input schema has no description for the single slug parameter, so the description must carry the parameter semantics. It only repeats that lookup is 'by slug' and does not explain expected slug format, casing, or constraints.

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 one pack by slug. It also clarifies that the result includes the EU AI Act checklist and verification block, which differentiates it from a generic pack listing.

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 'by slug' and 'one pack,' suggesting retrieval when a specific slug is known rather than listing or searching. However, it does not explicitly name list_packs or search_packs as alternatives or state when not to use this 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?

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorldHint=false, so safety is fully covered and the description adds no behavioral detail beyond that. Nothing is said about ordering, default result volume, pagination, or whether an empty result set is possible, so for a list operation the behavioral picture is only as good as 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 sentences, front-loaded with the operation and followed by the filter contract, with no filler. The parenthetical value lists are dense rather than verbose.

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 low-complexity, read-only list tool with strong annotations and no output schema, the definition supplies what an agent needs to make a valid call including the enumerated filter values. The remaining gap is the absent return-shape and result-volume expectations, which the missing output schema leaves entirely unaddressed.

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

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

Schema description coverage is 0%, so the description must carry the load, and it names all four parameters while supplying the allowed value sets for status (listed|submitted|verified) and tier (pilot|verified|verified+|reference) that the schema lacks entirely. It leaves the accepted format of the free-text platform and profession filters unexplained, hence not a 5.

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 opens with a specific verb and resource, 'List catalog packs', so the operation is unmistakable. It does not, however, distinguish this tool from the sibling search_packs, which an agent could easily confuse with a filtered list.

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?

'Optional filters' implies the two usage modes: call with no arguments to list everything, or narrow by one of the four fields. There is no explicit statement of when to prefer this over search_packs or when listing is inappropriate.

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 openWorldHint=false, so the safety profile is covered. The description adds that each profession carries decision types and a high-risk flag, which is useful content context, but it says nothing about result size, ordering, or whether the list is exhaustive.

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 no filler or redundancy. It is efficient, though quite terse given that no output schema exists to carry the return-value detail.

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, read-only list tool with no output schema, the description covers the essentials: what is listed and the key fields returned. Additional detail on response shape or volume would help but is not strictly required.

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 no parameters, so there are no semantics to explain and the baseline is 4. The description's role is limited to framing what the parameterless call yields, which it does adequately.

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 uses an imperative verb ("List") with a specific resource ("professions") and names the attributes returned: decision types and the AI Act high-risk flag. This is distinguishable from the pack-oriented siblings (get_pack, list_packs, search_packs), though the description never explicitly contrasts itself with them.

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 the verb and the resource; there is no explicit statement of when to use this versus the pack tools or any prerequisite context. With zero parameters and no obvious alternative for profession data, the omission is tolerable but not helpful.

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?

The annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is fully covered elsewhere. The description adds the useful detail of which fields are matched, but says nothing about matching semantics (substring vs token, case sensitivity), result limits or ordering. With annotations carrying the main burden, 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?

One sentence with zero filler, and the resource and search scope are front-loaded before any caveats. Nothing in it can be removed without losing information.

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 simple one-parameter read tool with full annotation coverage and no output schema, the description covers the essentials of what it searches. It falls short on result behavior, since limits, ordering and empty-result handling are undocumented and matter for an agent deciding how to consume the results.

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 0% for the single required 'query' parameter, so the schema alone gives no meaning. The description compensates partially by naming the three searchable fields, which tells the agent what the string is matched against, but it omits query syntax and whether multi-word input is ANDed, ORed or treated as a phrase.

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 (full-text search) and resource (packs), and adds the scope of what is searched: name, vendor and summary. That already separates it from get_pack, but the description never names list_packs or get_pack to make the sibling distinction explicit.

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: an agent can infer this is the tool for text queries rather than ID lookups, but the description never states when to prefer it over list_packs or get_pack. No exclusions, no prerequisites and no note on empty or no-match results.

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