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

The description explicitly states that setting mark_read:true flags returned events as read, a side effect that modifies state. However, the annotations declare readOnlyHint:true, implying the tool never mutates data. This is a direct contradiction between the description and annotations. Per the rubric, this mandates a score of 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 concise and front-loaded with the core purpose, followed by return details, filtering, mark_read behavior, and an alternative access point. Each sentence carries useful information, but it is a bit longer than necessary; a sentence about the alternative URL could be moved or trimmed. Still, it is well-structured and without 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 having no output schema, the description thoroughly explains what the tool returns (source, citation_uri, raw payload), provides filtering guidance, clarifies the side effect of mark_read, and offers an alternative URL for scripts/dashboards. Combined with thorough annotations (readOnlyHint, idempotentHint, openWorldHint) and 100% schema coverage, the description is complete for a list/feed 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% with descriptions for all 5 parameters. The description adds extra meaning beyond the schema by explaining the effect of mark_read (flagging read so next call shows newer ones) and contextualizing filter type with an example (sec_8k). It also describes the return payload, enriching the parameter context. This goes slightly beyond the baseline 3.

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 opens with a specific verb phrase 'Pull fired events from your subscription feed', clearly identifying the tool's action and resource. It also distinguishes itself from siblings like list_subscriptions or recent_changes by focusing on alerts from subscription feeds and describing their content (source, citation_uri, raw payload).

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 on when to use the tool: for polling recent alerts, with filtering options, and mark_read. It does not explicitly name a sibling alternative but indicates an alternative HTTP endpoint for scripts/dashboards, which offers practical guidance. However, it lacks explicit exclusions or when-not-to-use guidance, so it misses a 5.

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