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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety and side-effect questions are pre-answered. The description still adds real value beyond them by disclosing result semantics: ranked "best sections" rather than whole pages, each with a URL and an excerpt. It says nothing about ranking behavior, excerpt length, or behavior on zero matches, keeping it out of the top band.

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?

Two tight sentences with zero waste: capability and scope first, return shape second, routing hint last. Every clause carries information an agent needs, and nothing is repeated from the schema or annotations.

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 two-parameter, read-only search tool with no output schema, the description covers the essentials: what is searched, what comes back (URL + excerpt), and where to go for full pages. Annotations handle the safety profile and the schema handles parameter formats, so nothing an agent needs in order to call this correctly is missing.

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 100%: the query param already carries example queries ("return url", "element session discount", "webhook retries") and limit documents its range and default of 8. The description adds only the implication that queries are matched by relevance ("best sections"), which is modest incremental meaning over the schema. Baseline 3 is appropriate when the schema already does the parameter-level work.

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 ("Search the Terudo developer documentation") and enumerates the doc domains covered (Elements, partner API, webhooks, testing, AI tools, CLI), then describes what comes back (best sections with URL and excerpt). It also explicitly names the sibling tool it is not ("read a whole page with read_doc"), so an agent can separate it from read_doc 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?

"read a whole page with read_doc" gives an explicit alternative and the condition that selects it, which is the most likely confusion point given the sibling list. It does not address other plausible alternatives (list_docs, api_reference) or say when searching is the wrong first move, so it stops short of full when/when-not coverage.

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