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

Annotations already mark read-only, idempotent, open-world. Description adds meaningful context: returned events carry source/citation_uri/payload, mark_read side-effect, and the feed is persisted. No contradiction with annotations; the description enriches safety and state-change behavior.

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 tight paragraph, front-loaded with the core purpose, then specific details. Every sentence delivers value—no fluff or repetition. Appropriate length for 5 optional 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 the tool has 5 optional params, no output schema, and comprehensive annotations, the description covers the return payload (source, citation_uri, raw event), filtering logic, and read-state behavior. It is complete for a read-only polling 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 covers all 5 params with descriptions, so baseline is 3. The description adds an example filter value ('sec_8k'), clarifies mark_read's effect on the next call, and ties 'since' to 'fired_at', providing semantic nuance beyond the schema.

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 it 'Pull fired events from your subscription feed' with specific behaviors (filtering, mark_read), but does not explicitly differentiate from sibling tools like list_subscriptions or subscribe. The resource ('alerts') and verb are specific, yet without sibling comparison it's clear but not top-tier.

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?

It mentions when to use the tool ('Polls work fine') and points to an alternative REST endpoint for scripts/dashboards. However, it doesn't state when NOT to use the tool or contrast with sibling tools like list_subscriptions, so it's useful context but not explicit exclusions.

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