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

Annotations only declare that this is a non-read-only, non-destructive, non-idempotent write. The description goes well beyond them: notes persist until collection expiry, consumption counts against a 500-note lifetime limit even after deletion, a shared 60/min and 1000/day per-IP rate limit applies, and refusals may carry Retry-After. It also adds a data-handling warning about secrets and personal data.

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?

The batch size and token requirement are front-loaded, and each following sentence carries a concrete constraint. The closing 'No API key, no account and no sign up' is onboarding framing rather than invocation guidance, which is the only real 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, the description covers limits, persistence, and failure signalling well. It does not say what a successful call returns (assigned note identifiers, accepted versus rejected keys, remaining quota), which matters for a batch call where partial acceptance is possible.

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 would be 3, but the schema types the notes array only as generic objects while the description supplies the real item contract: a text field of 1-2000 characters and an optional key limited to 64 characters from a stated charset. That is genuine semantics the structured schema does not carry.

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 description opens with a specific verb and resource ('Add 1 to 32 notes') and states the scope of the write. An agent can tell this is the write path for a semantic search collection as opposed to query_semantic_search or delete_semantic_search_note, though it never names those siblings.

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?

Practical constraints (1-32 notes, 2000-character text, 500-note lifetime cap, 60/min and 1000/day limits) give a strong sense of when this tool applies, but there is no explicit routing guidance such as when to use this versus create_semantic_search or delete_semantic_search_note, and no statement of prerequisites beyond the token.

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