ask

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: it performs no model call (deterministic retrieval, no generation) and returns descriptions with IRIs rather than a synthesized answer.

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 compact sentence with a clarifying semicolon clause, front-loading the action and following with the key differentiator. 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 simple one-param read tool with no output schema, the description covers the essentials, but it leaves 'best-matching' undefined and does not clarify how results relate to sibling tools like 'search'. That missing routing context is the main 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 0%, but there is only a single parameter literally named 'question', which the description reproduces ('for a question'). It adds no format, length, or interpretation detail, but the param is self-explanatory, so a baseline 3 is fair.

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: returns descriptions of best-matching items for a question, citing item IRIs. That is concrete enough to distinguish it from pure retrieval or generation, but it never names or contrasts with the obvious sibling 'search', leaving the ask-vs-search boundary to inference.

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 guidance and no named alternative. The phrase 'no model is called' hints that this is a non-LLM path, but the agent is not told when to prefer 'ask' over 'search' or 'read'.

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