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

The description directly contradicts the annotation readOnlyHint:true by stating 'Set mark_read:true to flag returned events read so the next call only shows newer ones.' This implies a persisted state mutation, which is a write operation. No other side effects or behavioral caveats are disclosed, and the contradiction makes the description unreliable.

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 well-structured, starts with the primary action, and each clause adds useful information without excess wordiness. It is slightly dense (combining return fields, filtering, mark_read, and polling guidance) but remains readable and purposeful.

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 no output schema, the description compensates by listing the key fields returned (source, citation_uri, payload). It covers filtering, mark_read behavior, and polling. The main gap is no explicit mention of 'limit' or 'unread_only', but these are adequately documented in the input schema, so the description is sufficiently complete for a straightforward 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 description coverage is 100%, so baseline is 3. The description adds value beyond the schema by providing a concrete example for 'type' (sec_8k), clarifying that 'since' is an ISO timestamp, and explaining the practical effect of 'mark_read' on subsequent calls. It does not repeat all parameter details but supplements them meaningfully.

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' and clearly identifies the resource ('your persisted feed'). It further distinguishes the tool by noting returned fields (source, citation_uri, raw payload), making its purpose unambiguous compared to siblings like list_subscriptions or recent_changes.

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 concrete usage context: it explicitly states that polling works, explains how to use mark_read for incremental reads, and offers an external HTTP endpoint as an alternative for scripts/dashboards. It does not explicitly name sibling tools as alternatives, but the guidance is clear enough for an agent to decide when to use this tool.

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