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

The description adds substantial behavioral context beyond annotations, including authentication requirements ('Bearer API key is required'), rate limits ('each key may hold up to 50 watches'), callback signing behavior, and failure conditions ('Duplicate or unsafe webhook registrations are rejected'). These details (auth needs, rate limits, behavioral side-effects) are exactly the value-added context the rubric calls out. No contradictions with the annotations—in fact, the idempotentHint aligns with the duplicate rejection language.

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?

Four dense, information-rich sentences deliver purpose, auth requirements, limits, operational modes, error behavior, and an important exclusion (no immediate ingestion). Zero filler or redundancy—every clause earns its place. The structure frontloads the core action and layers details logically.

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?

Given the tool's moderate complexity (stateful watch creation with two operational modes) and the presence of a rich output schema that covers return values, the description covers the critical ground: auth, limits, mode selection, validation rejections, and non-ingestion behavior. Slightly more could be said about lifecycle management (e.g., how to identify or remove watches), but this is quite complete for a creation endpoint.

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?

With 100% schema coverage, the baseline is 3. The description enriches the webhookUrl parameter by clarifying the behavioral implications of omitting it (polling) versus providing it (signed POST callbacks), and it adds the watch-limit context tied to the serviceName scope. While the schema already documents format and examples, the description clarifies the semantic implications of each parameter choice, adding value above the schema.

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?

The description clearly states the tool's purpose with a specific verb+resource: 'Create a persistent specification watch for one service.' The scoping to 'one service' adds precision, but it does not explicitly differentiate from siblings like factreason_api_breaking_changes or factreason_deprecation_scan, which an ideal description might (e.g., noting this is for future changes vs. current analysis). Clear but lacking explicit sibling differentiation.

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 provides excellent context on how to use the tool—explaining the polling mode versus webhook callback mode ('Without webhookUrl... with a public HTTP(S) URL...') and the key/limit constraints. It even includes a 'when-not' with 'This does not ingest a specification immediately.' However, it never names alternative tools or says 'use tool X for Y,' falling just short of the explicit alternatives required for a 5.

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