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

With no annotations, the description carries the full burden and does well: it discloses case-insensitive all-words matching (speaker names count), newest-first ordering, surrounding-line context, the 150-call cap with partial-result signaling, and that secret notes are excluded. It does not mention pagination interaction with limit or latency, but the behavioral picture is substantially complete.

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 the core purpose and the return shape, and nearly every clause adds information (matching rules, ordering, context lines, cap, secret-note exclusion). It is a dense run-on pair of sentences, but little could be cut without losing guidance.

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 steps in to describe the return shape (note id/title, m:ss offset, speaker, line plus neighbors) and the partial-result signal. Combined with the mutation-free read nature and scoping params, an agent has nearly everything needed; only workspace defaults and limit interaction are left to the schema.

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 67%, and the description usefully compensates for the two undocumented params: query is defined as all-words, case-insensitive, speaker-name-inclusive matching, and person is clarified as 'on the call'. from/to/limit/workspace are already explained by the schema; workspace is not mentioned in the description, a minor omission.

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 ('find what was said on the user's calls: transcript lines') and enumerates exactly what a hit returns (note id/title, time into call, speaker, line plus context). This is clearly distinguishable from the sibling get_transcript, which would fetch a whole transcript rather than search across calls.

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?

Explains how to scope results via person/from/to ('person: on the call') and discloses the 150-call ceiling with the 'partial' flag. It gives clear usage context but never explicitly contrasts itself with get_transcript or search_notes, so the alternative-selection guidance is implied rather than stated.

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