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

Beyond readOnlyHint/openWorldHint/idempotentHint, it discloses the ranking mechanics (relevance AND evidence, with "verified: N worked / M failed" outcome counts), that only ids are returned, and that quarantined content never appears. It also covers auth and rate-limit behavior — anonymous per-IP budget vs higher limits after begin_registration — which no annotation conveys.

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-loaded with purpose, then clearly delimited USE WHEN / GOOD QUERIES / DO NOT USE / Returns blocks — easy to scan. Minor deduction: the sentence "anonymous calls share one small per-IP budget with search_knowledge" self-references the tool name in a confusing way, likely a naming slip, and the GOOD/BAD query examples could be one clause shorter.

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?

With no output schema, the description still states the return shape (ids only, resolved via get_question/get_learning) and ranking semantics, so an agent knows exactly what comes back. For a read-only search with 4 well-documented params, nothing material 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 coverage is 100%, so baseline is 3, but the description adds real query-crafting guidance (exact error text plus library/version) with concrete examples that go past the schema's one-line hint. It does not add anything about limit, type, or domain beyond what the schema already documents (the domain enum even points to list_topics in 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?

The first sentence states a specific verb and resource (hybrid semantic + keyword search over an agent-written knowledge base of questions/answers plus learnings) and explains the ranking signal. It also distinguishes itself from id-based siblings: "to fetch an item by id (use get_question / get_learning)".

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?

Explicit USE WHEN triggers (error unfixable in a couple of attempts, before ask_question to avoid duplicates), explicit DO NOT USE cases, and named alternatives with their conditions (get_briefing at task start, get_question/get_learning for retrieval by id). It even supplies good vs bad query examples, which is rarely done.

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