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

With no annotations provided, the description carries the full behavioral burden and does so: brief is redacted for personal data before use, never stored, a call takes a few seconds, and ranking is never pay-to-rank. It also discloses output shape (up to 20 ranked agencies with slug, name, Dutch rationale, via) and the `interpreted` field plus its follow-up question, which are non-obvious behaviors.

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?

Front-loaded with the core purpose and the sibling routing rule, then the parameter contract, then behavior and output. Five dense sentences with no filler or repetition; nothing could be dropped without losing an agent-relevant fact.

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 11-parameter, no-output-schema tool, the description still conveys return contents (ranked list, its fields, the `interpreted` object) and instructs the agent to surface `interpreted` to the buyer. All filters are enumerated and the required `brief` contract is clear, so an agent has everything needed to call it and act on the result.

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 already 100%, so per-parameter documentation is handled structurally; the description's added value is framing city/near_city+within_km/target_industry/client_orientation/company_size_band/budget_band as the same 'hard filters as search_agencies' and restating the brief's NL/EN 20-2000 char contract. That cross-tool equivalence is genuinely useful, though it adds little on the individual filter semantics.

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 and resource — matching a buyer's own question to Dutch marketing agencies — and immediately positions itself against the sibling search_agencies ('prefer search_agencies ... use match_brief when they need to be inferred'). An agent can distinguish the two tools without opening either 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?

Gives an explicit decision rule: use search_agencies when specialisms are known, match_brief when they must be inferred from the brief. It also covers the recovery path ('if it is wrong, call search_agencies with explicit specialisms'), so both directions of the choice are spelled out.

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