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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the bar for additional disclosure is lower. The description adds meaningful behavior beyond that: results come from a semantic/vector pipeline rather than exact keyword matching, search spans all accessible workspaces, and conversation context persists via conversation_id. No contradiction with annotations.

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?

Three sentences with zero waste: core purpose front-loaded, then the search mechanism, then the follow-up capability. Nothing repeats schema content or annotation data.

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?

Annotations cover the safety profile, an output schema exists, and all parameters are documented, so the description only needed to cover scope, mechanism, and follow-up mechanics — which it does. It falls just short of 5 because it leaves unresolved what within a note is searched (content vs. title vs. metadata) and provides no alternative routing guidance.

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 description coverage is 100%, so all four parameters are already documented in the schema; per calibration, the baseline is 3. The description lightly reinforces conversation_id's follow-up role and implies query should be phrased as natural language, but adds little meaning beyond what the schema already provides.

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?

'Search notes using natural language' pairs a specific verb with a distinct resource and states the search approach and scope: 'across all accessible workspaces,' with 'semantic/vector search powered by Typesense embeddings.' This clearly differentiates it from sibling search tools targeting other resources, such as search_documents, search_files, and search_collectplus_items.

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?

The description establishes clear usage context: it is for natural-language semantic search over notes across workspaces, and for follow-up questions via conversation_id. However, it never explicitly says when to prefer this over the four sibling search tools or when not to use it, leaving the routing decision entirely to inference.

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