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

Goes well beyond the annotations (which only signal non-read-only, non-idempotent, non-destructive). It discloses the 24-hour non-extendable lifetime, that read/write bearer tokens are returned once and must be kept secret, the 500-note cap, the 20-collections-per-IP limit, and the model-fixing behavior. These are exactly the operational constraints an agent needs before calling.

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 purpose, then lifetime, model, return values, limits and auth in a compact flow. Slightly dense and the model enumeration partially repeats the schema, but nearly every sentence carries distinct, decision-relevant information.

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 compensates by explaining that it returns a collection_id and separate read/write tokens, plus all lifetime, quota and auth constraints. Nothing an agent needs to call this correctly is missing.

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% and the enum plus default are already in the schema, so baseline would be 3. The description adds meaningful semantics by noting the model 'stays fixed for the collection', which is behavioral information the schema does not convey.

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 (Create) and resource (a semantic search collection) and immediately clarifies what it holds: short notes that agents search by meaning across wording and languages. This clearly distinguishes it from siblings like add_semantic_search_notes, query_semantic_search 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 context – 'call it directly' with no API key, account or signup – which tells the agent this is a frictionless entry point. It does not, however, explicitly state when to use this versus the add/query/read siblings or that it must precede them, so usage is clear but not fully routed.

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