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

Annotations already indicate readOnly, idempotent, openWorld, and non-destructive. The description adds valuable context: the mark_read behavior that alters future calls, the return fields, and that polls work fine. 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 3-4 sentences, each serving a purpose: main action, return fields, filtering options, side-effect, and alternative access. No redundant words. Front-loaded with the primary purpose.

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?

For a read-only list tool with no required params and no output schema, this description covers everything: what it returns, how to filter, side-effects, polling suitability, and an alternative endpoint. It equips an agent to select and invoke the tool correctly without gaps.

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% for 5 parameters. The description adds context beyond the schema: an example for type ('sec_8k'), explains the ISO timestamp requirement for 'since', and clarifies that mark_read flags events as read to affect subsequent calls. This enriches the schema definitions.

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 opening sentence 'Pull fired events from your subscription feed' clearly states the verb and resource. It specifies the tool's output (source, citation_uri, raw payload) and distinguishes it from sibling tools like 'list_subscriptions' which would manage subscriptions rather than fetch events.

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 explains filtering by type and ISO timestamp, and the mark_read side-effect for polling. It mentions an alternative URL for scripts/dashboards. However, it does not explicitly state when NOT to use this tool vs other sibling tools, though the context is clear enough.

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