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), so the bar is lower; the description still adds real behavioral context by disclosing the result cap ('up to three') and the shape of what comes back (each guide's own short answers and its address).

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 dense sentence carrying purpose, examples and return shape, followed by one short negative-scope sentence. No filler, and the core purpose 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 one-parameter read-only lookup with no output schema, the description supplies enough: scope, admission criteria for queries, result count and content. Minor gaps remain, such as behavior when no guides match or how to broaden a failing query.

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 the baseline would be 3, but the description goes beyond the schema's terse 'The question, in plain words' by showing the kinds of natural-language questions the query parameter accepts, which helps the agent phrase input.

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 (finds) and resource (BuildBatch's guides), scoped to decorating/flooring questions, and illustrates with concrete question types. It also stakes out a clear boundary ('does not work out quantities for a room') that separates it from plan_room.

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 concrete example questions ('how long between coats', 'how many tiles in a square metre') tell the agent exactly when this tool applies, and the closing sentence gives an explicit when-not boundary. It stops short of naming the alternative tool that should handle quantity work.

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