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

Annotations already declare readOnly=True, idempotent=True, destructive=False. The description adds beyond this by explaining the mark_read side effect (flags events read) and polling safety ('Polls work fine'), which are useful behavioral details. No contradictions with annotations.

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 a single paragraph of four sentences, efficiently front-loading the main purpose. Every sentence adds value (output shape, filtering, mark_read, poll safety). No fluff; appropriately concise for a tool with five parameters.

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 usefully describes the return fields (source, citation_uri, payload). It explains filtering, mark_read, and polling. Slight gap: limit parameter behavior is only in schema, not elaborated in description (e.g., pagination). Otherwise complete for a read-only 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%, so baseline is 3. The description does not add significant parameter meaning beyond the schema; it reiterates filtering by type (with example 'sec_8k') and since, but this is already clear from schema. No additional parameter semantics.

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 clearly states the tool pulls 'fired events from your subscription feed', specifying the resource and action. It mentions return fields (source, citation_uri, payload) but does not explicitly distinguish from sibling tools like 'recent_changes' or 'list_subscriptions', so not a 5.

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 notes 'Polls work fine' and mentions an alternative HTTP endpoint, but provides no guidance on when to use this tool versus sibling tools (e.g., when to use list_subscriptions instead). No exclusions or when-not-to-use advice is given.

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