ISMS Directory

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

Annotations already declare readOnly, idempotent, non-destructive, non-open-world, so the safety profile is covered. The description adds genuine value beyond that by disclosing the three possible outcome branches (listing, close matches, submission URL), which matters since there is no output 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?

Two sentences, zero filler, purpose front-loaded and the return branches compactly stated. 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?

For a single-parameter, read-only lookup with no output schema, the description covers the essential behavior: the three possible responses. Combined with annotations that cover safety, nothing critical is missing 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% with a single well-documented parameter ('Company or product name to look up'), so the baseline of 3 applies. The description adds no syntax, format, or disambiguation 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 ('Check whether') and resource ('a company is listed in the ISMS Directory'), which cleanly separates it from the service/category-oriented siblings (get_service_details, list_categories, search_services). An agent can tell what this does without opening the 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?

The purpose implies the usage context (verify listing status of a company), but there is no explicit when-to-use, when-not-to-use, or mention of an alternative such as search_services that could also surface company data. Guidance is implied rather than stated.

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 the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds genuinely non-obvious behavior: case-insensitive name matching and partial-name fallback, which affects how the agent should call it. It does not say what happens on ambiguity or no match, keeping it short of 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?

Two well-front-loaded sentences: first the payload, then the matching rule. No filler and nothing repeated from the title.

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-param read tool with full annotations, the description is nearly complete: it covers output fields and lookup semantics. It only omits failure behavior (no match, multiple partial matches), a minor gap given no output schema exists.

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 baseline is 3, but the description adds matching semantics (case-insensitive, then partial) beyond the schema's 'service or company name as listed', which is real added meaning for the sole parameter.

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 (get) and resource (full public profile of one listed service), and enumerates the returned fields so the agent knows exactly what this returns versus sibling search_services or check_if_listed.

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 phrase 'one listed service' implies a single-record lookup versus the list-based search_services, but no explicit when-to-use or when-not-to-use statement, and no sibling is named as an alternative.

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 closed-world, so safety is covered. The description adds genuine behavioral context beyond them: the return payload is tag names paired with per-tag service counts, which matters for interpreting results.

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, zero filler. The core action and return shape come first, with the consumer guidance second.

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, but the description partially compensates by describing the returned structure. It does not mention ordering, counts scope, or pagination, which are minor gaps for a simple one-parameter enumeration tool.

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 'dimension' parameter has a full enum listing all five values, so the schema does the heavy lifting. The description only reinforces the notion of 'one catalog dimension' without adding format or default detail.

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 ('every tag used in one catalog dimension'), plus the returned payload ('the number of listed services carrying it'). This is distinguishable from search_services, which consumes the tags rather than enumerating 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?

Explicitly routes the agent forward: 'Use the returned tags as exact filter values for search_services.' That is a clear use-case link, but it gives no when-not guidance or prerequisites (e.g., whether a catalog must be selected first).

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 adds non-obvious behavior beyond that: filters are exact tags, multi-framework queries combine with AND, and results are sorted by name rather than ranked relevance. Not revealing, but genuinely additive.

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 what is searched, then the tag semantics, the routing hint, and the sort guarantee. 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?

For an openWorldHint=false read tool with a fully documented schema and no output schema, the description covers purpose, filter semantics, result ordering, and a routing hint to list_categories. It omits any mention of result shape or how q maps to matched dimensions, but the essentials for correct invocation are 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?

Schema coverage is 100%, so baseline is 3, and the description earns above baseline by clarifying that all filters are exact tag matches and that frameworks are AND-combined — semantics that are only partially echoed in the schema. It does not add per-parameter detail for q/limit/regions/service_types beyond what the schema already says.

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 and domain: 'Search the ISMS Directory catalog of ISO 27001, SOC 2, GDPR, DORA, NIS 2 ... compliance service providers (consultants, auditors, platforms, training).' It also names the sibling list_categories and its role, so an agent can separate this from the lookup 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?

Explicitly routes tag discovery to list_categories ('Use list_categories first if you are unsure of a tag') and warns filters are exact tags, which is real usage guidance. It does not state when NOT to use this tool versus get_service_details or check_if_listed, so it stops short of full when/when-not coverage.

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