subscriptions

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

No annotations are provided, so the description carries the full behavioral burden. It does add the useful scoping detail that results are limited to what *this session* has watched, but it omits ordering, size limits, and what the entries contain.

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?

A single sentence with zero waste, front-loaded with the verb and resource, and carrying the one qualifier that matters (session scope).

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?

The tool is trivially simple — no parameters, no annotations, no output schema — so the description is not dangerous, but with no output schema it should at least sketch what a listed pull request looks like or in what order they return. As written the agent knows what it gets in aggregate but not the shape of the result.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The only semantic content is the scope of the list, which the description does state.

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 pair ('List pull requests watched by this session') and the session scoping implicitly separates it from the subscribe/unsubscribe siblings, which mutate that watch list. It does not explicitly name those siblings, so an agent still has to infer the pairing.

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?

Usage is only implied: the description makes clear this is the read side of the subscribe/unsubscribe pair, but it never says when to call it versus pending_events, nor whether it is safe to call at any time. No explicit when/when-not guidance.

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