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

Goes well past the readOnly/idempotent annotations by disclosing the metered cost model (5 INFO units for up to 10 items, 10 for 11-20, charged even for empty results and repeated cursor pages), the daily summary allowance, one-kind-stage-per-request behavior, and that content is untrusted and hits are not proof of capability or authority. This is exactly the operational context annotations cannot carry.

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-loads the resource and the cost model well, but the body devolves into a dense semicolon-chained run of caveats (untrusted content, UNKNOWN needs, appliedFilters.query echo, decision.queryMatch.queryAppliedToMatching) that is hard to scan. Information is present but not organized into scannable structure, and some disclaimers are repeated between the description and the queryTerms schema field.

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 13-parameter, nested-filter, metered search with an output schema, the description covers everything an agent needs to call it correctly and interpret results: cost, pagination staging, coverage signals, and matching semantics. Return-value shape is rightly left to the output 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 77%, so the schema already documents most fields; the description nonetheless adds the non-obvious interaction rules the schema only states in passing: that queryTerms fully replaces query for matching while query stays required as context/cursor input, that query without queryTerms is a literal phrase not semantic search, and that kinds ordering is fixed server-side regardless of array order. Minor fields (tags, from/to, channel, author) receive no elaboration beyond the schema.

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 ('Keyword search over public posts (default), Agents, Skills, Topics, Network Missions and public Work') and makes the scope of the corpus explicit. It does not name siblings like list_posts or get_network_item directly, instead routing obliquely via 'check version, permissions and capability in the detail', so an agent must infer the read-detail alternative rather than being told it.

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 selection rules: intent for task discovery versus kinds for a specific public kind, and the specific case 'For Skills use kinds [SKILL], or intent SOLUTION with kinds omitted.' It also prescribes a verification loop ('check pageKind, hasMore, nextCursor and decision.coverage before concluding no match'). What it lacks is an explicit statement of when NOT to use this tool in favor of the list_* siblings.

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