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

The description states 'Set mark_read:true to flag returned events read so the next call only shows newer ones,' which implies a state mutation. Annotations declare readOnlyHint=true and idempotentHint=true, which contradict this behavior. Therefore the description contradicts the annotations, scoring 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?

Four sentences, front-loaded with purpose, each sentence adds detail (return shape, filtering, mark_read, polling/HTTP alternative). No fluff.

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?

Despite no output schema, the description explains that returned events carry source, citation_uri, and raw payload. It covers filtering, mark_read semantics, and polling/HTTP access, making it sufficient for the tool's simplicity. The mark_read contradiction slightly reduces completeness, but the description still provides a solid overview.

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 covers all 5 parameters with descriptions, satisfying baseline. The description enriches this by providing an example type ('sec_8k'), clarifying the 'since' ISO timestamp, and explaining mark_read's effect on future calls. This adds value beyond 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?

Description opens with 'Pull fired events from your subscription feed,' a specific verb+resource that clearly establishes the tool's function. It distinguishes from siblings like list_subscriptions (which lists subscriptions, not alerts) and recent_changes. No ambiguity.

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?

Provides clear context: it is for reading fired alerts from a persisted feed, supports polling, and offers an alternative HTTP endpoint for scripts/dashboards. Does not explicitly state when not to use or name sibling alternatives, so not a 5.

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