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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely new behavior: the search is semantic rather than lexical, and an empty result means the workspace truly has nothing stored rather than being a failure to retry or work around. Return shape and ranking behavior are 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?

Front-loads what is searched, then when to use it, then how to phrase the query, then the empty-result caveat — a sensible priority order. Every sentence carries actionable information, including the trailing clause about not working around an empty result.

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 2-parameter read-only retrieval tool with full annotation coverage, the description covers purpose, trigger, phrasing, and the null-result case. The one remaining gap is that no output schema exists and the description never says what a passage looks like (source attribution, snippet form), which an agent would want before quoting results.

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 the baseline is 3, but the description adds real meaning: the query need not use index terms because matching is by meaning, so the user's own phrasing should be passed through. The limit parameter's effect ('how many passages to return') is left entirely to the schema, which adequately documents it.

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 ('Searches what this workspace has stored') and enumerates the content types covered (notes, pages, documents, product details). It also distinguishes the retrieval mode ('searches by meaning'), which separates it from a keyword or listing tool. It never names the sibling list_knowledge, so sibling differentiation is implied rather than explicit.

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 a clear trigger ('Use it before writing anything factual about them') plus explicit alternatives to avoid ('rather than guessing or asking'). It also pre-empts the empty-result case ('worth saying rather than working around'). It does not cover when to prefer list_knowledge for enumeration, so the routing guidance is incomplete.

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