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

Adds substantial behavior beyond the annotations: the 500-note lifetime limit that counts deleted notes, retention until collection expiry, rate-limit budget shared with search, Retry-After on refusals, and a secrets/PII warning. Annotations only confirm it is a non-idempotent, non-read-only, non-destructive write.

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 but front-loaded: batch size, auth, note shape, then limits, rate limits, and retry policy in order of importance. Nearly every sentence carries actionable information, though the closing 'no API key, no account, no sign up' line is marginal padding.

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 mutation tool with no output schema and thin annotations, the description covers auth, limits, retention, rate limiting, and failure handling well. It stops short of explaining what a reused note key does (upsert vs. duplicate) — a notable gap given the non-idempotent annotation.

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 goes further by documenting constraints the schema omits: text of 1-2000 characters, an optional key of up to 64 allowed characters, and the 1-32 batch bound. The write_token's role is also spelled out beyond the schema text.

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 ('Add ... notes') with the target ('semantic search collection') and batch semantics. It is trivially distinguishable from siblings like create_semantic_search, query_semantic_search, delete_semantic_search_note, and read_semantic_search.

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 strong operational usage context: the write token is required, sharing a 60/min and 1000/day per-IP budget with search, refusal Retry-After handling, and an explicit 'do not retry automatically' instruction. It does not explicitly name when to prefer a sibling (e.g. delete or query), but the tool's scope makes that largely implicit.

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