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

Annotations already declare safe read-only behavior (readOnlyHint, non-destructive). The description adds valuable context: mark_read flags events read affecting next call, polling is supported, and the same feed is available via GET endpoint. No contradictions.

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?

Three concise sentences: first introduces purpose and returned fields, second explains filtering, third covers mark_read and alternative access. Every sentence earns its place, no redundancy.

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 specifies return fields (source, citation_uri, payload) and covers filtering, mark_read, unread_only, and polling. Lacks explicit limit defaults but schema provides that. Missing error handling context but adequate for the tool's simplicity.

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 parameters with descriptions. The description enriches by giving a concrete example for type ('sec_8k') and explaining mark_read's effect on future calls. This adds practical 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 the tool pulls fired events from the subscription feed and returns recent alerts with key fields. It distinguishes itself from siblings like list_subscriptions and recent_changes by focusing on alerts and mentioning an alternative REST endpoint for scripts/dashboards.

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 explicit filtering options (type, since) and explains the mark_read behavior for subsequent calls. It also notes that polling works fine and gives an alternative access method, but does not explicitly contrast with sibling tools like recent_changes.

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