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

The annotations already indicate the tool is read-only, idempotent, and non-destructive. The description adds significant behavioral context: it specifies the exact data returned (source, citation_uri, payload), explains that mark_read flags events for the next call, and confirms polling is acceptable. It also mentions an alternative HTTP endpoint, providing extra transparency.

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 4 sentences and efficiently conveys the core purpose, return data, filter options, and mark_read behavior. The last sentence about the HTTP endpoint is slightly tangential but still useful context. It is well-structured and front-loaded with the main action.

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 the tool has 5 parameters and no output schema, the description provides adequate context: it mentions the return fields, filter parameters, mark_read effect, and polling suitability. It does not explicitly explain the limit parameter (covered in schema) or pagination, but the overall context is sufficient for an agent to invoke the tool correctly.

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 clear descriptions for all 5 parameters. The description summarizes some parameters (type, since, mark_read) but does not add meaningfully beyond what the schema already provides. It restates mark_read's behavior which is already in the schema, so no significant added value.

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 a subscription feed and returns the most recent alerts with specific fields (source, citation_uri, raw event payload). This is a precise verb+resource description that distinguishes it from siblings like list_subscriptions (which likely manages subscriptions rather than retrieving alerts).

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: it mentions filter options (type, since), mark_read behavior, and notes that polls work fine and the same feed is available via HTTP. However, it does not explicitly say when to use this tool versus alternatives or when not to use it, missing some usage boundaries.

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