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

Annotations already mark read-only, and the description goes further: single-page/no-pagination behavior, 'Scores are only comparable within one response', and 'English queries rank best'. These are genuine non-obvious behaviors an agent cannot infer from schema or 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?

Every sentence carries operational value: purpose, result bound, example, date-mode usage, troubleshooting, and ranking caveat. It is front-loaded and free of boilerplate.

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 13-parameter search with no output schema, the description covers the essential behaviors: result cap, pagination absence, relevance mode, sort-by-date mode, and score comparability. Minor gaps remain around default sort and exact result fields, but the example and caveats make calling it correctly feasible.

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?

The description gives a concrete invocation example ('{query: "pasta recipes", source: "youtube", limit: 5}') and explains query omission semantics, adding meaning beyond the schema. It does not detail every filter, but schema descriptions cover 62% of parameters and the example fills the practical gap.

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 ('Search') and resource ('the user's MarkIt library') and adds result semantics ('Returns up to 30 ranked results in a single page'). It is clearly distinct from siblings like save_item and fetch.

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 an explicit alternate invocation mode: 'OMIT query to list the newest saves in date order (use this for "what did I save recently/last")'. Provides retry guidance for empty/failed results and a language caveat, but does not explicitly contrast with alternatives such as fetch for exact retrieval.

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