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

The description reveals a state-changing behavior: 'Set mark_read:true to flag returned events read' which modifies the feed state. This directly contradicts the annotation readOnlyHint=true, which declares the tool as read-only. The annotation misleads agents into assuming no side effects, while the description discloses a conditional mutation. This is an annotation contradiction.

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 compact and front-loaded with the core purpose. It covers return fields, filter options, mark_read behavior, polling note, and an alternative endpoint in just three sentences, with no redundant or filler content.

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?

For a tool with 5 optional parameters and no output schema, the description provides essential return structure (source, citation_uri, raw payload), filtering guidance, mark_read side effects, and polling advice. It lacks a mention of unread_only, but the schema covers it. However, the annotation contradiction reduces trust and completeness, so it's not a perfect score.

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 baseline is 3. The description adds meaningful semantics beyond the schema, especially for mark_read: 'so the next call only shows newer ones' explains the consequence of flagging read. It also gives a concrete example for type ('sec_8k') and mentions ISO timestamp for since, enhancing the schema's descriptions.

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 and resource: 'Pull fired events from your subscription feed.' It clearly distinguishes itself from siblings like recent_changes and list_subscriptions by focusing on alerts with citation_uri and raw event payloads. It also mentions the persisted feed, making the tool's scope unambiguous.

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 usage context: 'Polls work fine' indicates suitability for repeated checks, and the alternative GET endpoint offers a non-polling option for scripts/dashboards. However, it does not explicitly contrast with sibling tools like recent_changes or list_subscriptions, though the unique functionality is clear.

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