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

Annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, but the description states that setting mark_read:true will 'flag returned events read so the next call only shows newer ones,' which mutates state and makes the tool non-idempotent across calls. This directly contradicts the readOnly and idempotent annotations, so the score is 1.

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?

The description is three sentences and front-loaded with the core purpose. Each sentence adds useful information: what the tool returns, how to filter, and the availability of an HTTP endpoint alternative. It is concise without sacrificing key details, though the HTTP endpoint sentence is somewhat tangential.

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 lack of an output schema, the description adequately explains the return value structure (source, citation_uri, raw payload). It explains mark_read behavior and mentions polling suitability. It could have described limit behavior or unread_only, but the schema covers those, so the description is sufficiently complete for a simple retrieval tool.

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%, so the baseline is 3. The description adds meaningful extra context: it provides a concrete example for type ('sec_8k'), clarifies since as an ISO timestamp, and explains the effect of mark_read:true on subsequent calls. It does not cover limit or unread_only, but those are adequately described in the schema, so the description adds enough to warrant a 4.

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 starts with a specific verb 'Pull' and clearly identifies the resource: 'fired events from your subscription feed.' It also explains the return contents (source, citation_uri, raw payload) and distinguishes itself from siblings like list_subscriptions by focusing on alerts rather than subscription management.

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 clear context for when to use the tool: filtering by type and since, using mark_read to control subsequent calls, and noting that polling works fine. It also mentions an alternative HTTP endpoint for scripts/dashboards, giving explicit guidance on alternative access. However, it doesn't explicitly contrast with sibling tools beyond that.

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