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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint=false), and the description adds genuinely useful context: no API key or account needed, the read token is required and comes from create_semantic_search, and results are capped at 10. However, it spends much of its length on scoring arithmetic rather than on operational behavior such as failure modes for an invalid or expired token.

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?

Purpose and result shape are front-loaded, which is good, but the middle is a dense block of scoring rules including edge cases like '1 200 read as 1200' that cost more attention than they return for tool selection. It is one undivided paragraph with no separation between what the tool does, what it returns, and how to interpret scores.

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?

There is no output schema, and the description fully compensates by naming the return fields (note_id, key, text, score) and explaining what the score means and its limits. Combined with annotations covering read-only and idempotent behavior, an agent has everything needed to call this correctly and interpret 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 all four parameters and their bounds are already documented in structured form. The description restates the limit range and default ('1 to 10 and 3 by default') and mentions the read token without adding format or provenance detail beyond what the schema provides. Baseline 3 is appropriate.

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 ('Search the notes by meaning') and the credential it uses, so the operation is unambiguous. It does not explicitly differentiate itself from sibling read_semantic_search or add_semantic_search_notes, leaving the agent to infer that this is the ranked-retrieval path rather than the direct-read path.

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?

It gives real usage guidance in the caution that results are 'ranked suggestions, not a decision that a match exists: read the text before acting on it', which tells the agent how to treat output. It never states when to prefer this over read_semantic_search or add_semantic_search_notes, so alternative selection is left implicit.

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