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

Annotations already indicate readOnlyHint, idempotentHint, and destructiveHint. The description adds valuable behavioral details: the mark_read flag to acknowledge events so subsequent calls show only newer ones, and the structure of returned events (source, citation_uri, payload). 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 somewhat verbose (multiple sentences) but well-structured: purpose first, then details, then alternative. A more concise rewrite could improve readability without losing information, hence a 3.

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 no output schema, the description explains return fields (source, citation_uri, payload) and all parameter behaviors, including mark_read semantics. It also provides an alternative endpoint for scripts/dashboards, making it fully self-contained for a read-only 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?

Since schema coverage is 100%, the baseline is 3. The description adds extra context for mark_read by explaining its effect on subsequent calls, and mentions filtering by type and since. This slight enhancement justifies a 4.

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, returning recent alerts with specific fields (source, citation_uri, payload). It uses specific verb+resource (pull/recent alerts) and distinguishes itself from sibling tools, none of which directly handle 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 usage context by mentioning that polling works fine and offering an alternative endpoint (GET alerts.json) for scripts and dashboards. It does not explicitly state when not to use this tool but implies appropriate use cases.

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