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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuine value beyond that by disclosing the return shape ('grounded summaries and citation URLs') and by scoping out customer accounts and photos. It stops short of mentioning result limits or that at most 6 results come back.

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 sentences, no filler: purpose first, return shape second, scope exclusion last. Each sentence carries distinct information and the most important content 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 simple three-parameter search tool, the definition covers purpose, return values (no output schema exists, so this matters), and exclusions, while annotations handle the safety profile. The remaining gap is parameter behavior (limit ceiling, optional room filter), which is small given the self-descriptive enum and bounded integer.

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 carries the full burden, and it does not explain any parameter. The 'room' enum values, the optional nature of 'room', the default/maximum of 'limit', and the 2-200 character bound on 'query' are all left to the raw schema. Topic words like 'kitchen storage' hint at the room filter but never state it.

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?

Names a specific verb ('Search') plus a precisely scoped resource ('ABIS public interior planning answers') and enumerates the covered topic areas (room layout, kitchen storage, lighting, cost factors). The closing exclusion ('Does not search customer accounts or photos') further sharpens the boundary, so an agent can distinguish this from the get_interior_answer and get_interior_styles siblings 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?

The topical scope implies when to reach for this tool (open-ended interior questions), and the negative scope rules out account/photo lookups. However, it never names the alternatives or states a selection rule against get_interior_answer (which presumably fetches a specific answer) or get_interior_styles, leaving the routing to inference.

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