search_content

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered structurally. The description adds genuinely new behavior beyond that: a hard cap of 20 results with no paging, the meaning of `capped: true`, and that stance hits on polls with hidden results are DROPPED from query searches. That is real added value, though the return shape of individual results is left unstated.

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?

Dense and front-loaded: scope, then parameter modes, then the cap, then the exclusion caveat. Each sentence carries information, though the phrasing is telegraphic enough that some clauses (e.g. 'Stance hits on polls with hidden results are DROPPED') require a second read.

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?

There is no output schema, so the description reasonably must mention return behavior — it covers the 20-result cap and the `capped` flag, but does not describe what a result item looks like or how `relevance` ordering interacts with the cap. For a six-parameter search tool with full schema coverage, this is close to sufficient.

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%, so the per-parameter baseline is 3, but the description adds combination semantics the schema does not: `author_id` alone yields that author's 20 newest items, and query+author_id compose. It also reinforces the prefix-match and `!word` exclusion syntax and ties the result cap to the `capped` flag.

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 (keyword search) and resource scope ('everything the connector's user can see'), and explicitly contrasts with the enumerate-style siblings by noting it is a single call reaching all record types. An agent can immediately tell this apart from list_discussions/list_polls/get_* tools.

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 concrete invocation modes: pass `query`, pass `author_id` alone for 'what did X post', or both. It also states an explicit prohibition ('never use search to probe hidden vote reasons'), which is the kind of when-not guidance most descriptions omit.

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