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

No annotations are provided, so the description carries the full burden; it prominently discloses read-only behavior, that nothing is sent to partners, the cap of 5 results, and that match reasons are returned. It does not cover determinism, rate limits, or error behavior, so it is strong but not exhaustive.

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 tight sentences, with the core output shape front-loaded and the routing hint last. No filler or restatement of 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 no-output-schema, no-annotation tool with 8 inputs, the description covers the output and safety profile well but leaves the input contract largely unexplained. An agent can pick the tool, yet must infer parameter meaning entirely from the enum lists.

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 only 13% across 8 parameters, so the description must compensate and adds essentially nothing about inputs. Enum values are largely self-describing (country, industry, employees, situation), but there is no explanation of how any input shapes the matching, nor of optional filters like apps, languages, or ai_assisted_delivery.

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+output shape: a rule-based shortlist of up to 5 partners for a buyer's project, with reasons. It also names a sibling (prepare_request) for the adjacent contact action, letting an agent distinguish it from search_partners and prepare_request.

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 frames the tool's role ('read-only, nothing sent') and routes to prepare_request when the buyer needs to contact partners. It lacks an explicit exclusion against search_partners/directory_stats, so it stops short of full when-not guidance.

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