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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds value beyond that with the corpus size, the 'evidence-checked' data-quality claim, and the return shape (ranked agencies, a per-match reason, a profile link), which matters given there is no output schema. It omits the result cap implied by limit and any freshness/ranking caveats.

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 capability and scope front-loaded, followed by filters and return shape. No filler and no repetition 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 read-only search tool with no output schema, the description covers the corpus, the filter surface, and the return format including the ranking rationale, which is what an agent needs to plan a call and interpret results. The main omission is the 1-10 limit ceiling and default, which an agent must read from the schema.

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 80%, so per-parameter meaning is largely handled structurally. The description reinforces this by enumerating the filters (country, tool, budget) and supplying concrete values for tool (n8n, Make, Zapier, Retool, Vapi) and currency for budget (USD), but says nothing about limit, leaving one parameter undocumented in both places.

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: searching a named corpus (960+ evidence-checked AI automation agencies on Cofounderbase) by a plain-English need. The exploratory, query-driven nature implicitly distinguishes it from get_agency (single lookup) and top_agencies (presumably a ranked list), though no sibling is named explicitly.

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 framing 'by a plain-English need' plus the list of optional filters implies the intended use case, and the filter list suggests when to narrow results. However, it never says when NOT to use this tool, nor does it route the agent to get_agency, top_agencies, or request_intro.

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