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

Annotations already declare readOnlyHint=true, but the description discloses a subtle side effect: setting mark_read:true flags events as read and affects the next call's results. This adds context beyond annotations. It also mentions the persisted feed and provides the HTTP endpoint, but does not cover auth requirements or rate limits.

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 four sentences, each serving a purpose: main action, return payload, filtering/mark_read, and alternative endpoint. It is front-loaded with the core purpose and keeps details concise. A slight deduction for mixing filtering and external endpoint details into one long sentence, but overall efficient.

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?

With no output schema, the description adequately covers return values (source, citation_uri, raw payload). It also explains filtering, mark_read, and polling behavior. Missing some context on unread_only and potential parameter interactions, but the schema covers those. This is a well-rounded description for a 5-parameter optional 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 coverage is 100%, so baseline is 3. The description enriches the parameters by giving an example filter type ('sec_8k'), clarifying the 'since' parameter as an ISO timestamp, and explaining the effect of mark_read:true. It does not mention limit or unread_only, but these are well-documented in 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 opens with a specific verb and resource: 'Pull fired events from your subscription feed.' It clearly states what the tool returns (recent alerts with source, citation_uri, raw payload). It is distinct from sibling names like list_subscriptions or recent_changes by focusing on fired alerts from a persisted feed.

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 gives clear context on when to use this tool (pulling alerts, filtering, marking read) and even mentions an alternative endpoint for scripts/dashboards. However, it does not explicitly contrast with sibling tools such as list_subscriptions or recent_changes, so alternatives among the tool list are not named.

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