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

Annotation Contradiction: The annotations declare readOnlyHint=true and idempotentHint=true, but the description states that setting mark_read:true flags returned events read, which mutates feed state and affects future calls. This contradicts the read-only hint. The description otherwise gives useful context (polling, payload details), but the contradiction forces a score of 1 per rubric.

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 compact and front-loaded: the first sentence states the verb, resource, and return shape. It uses four purposeful sentences without padding, and each sentence adds distinct value (purpose, filters, mark_read, polling/alternative endpoint).

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 having no output schema, the description explicitly states what each alert carries (source, citation_uri, raw event payload), covers filtering, read-state handling, and polling behavior. With five optional parameters and no required inputs, this is sufficient context for an agent to use the tool correctly.

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 description coverage is 100%, so baseline is 3. The description adds operational meaning beyond the schema: it explains that 'since' takes an ISO timestamp, gives an example for 'type' (sec_8k), and clarifies the downstream effect of mark_read (next call only shows newer ones). This is meaningful added semantics, though it does not cover every parameter.

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 uses a specific verb ('Pull') with a clear resource ('fired events from your subscription feed') and immediately distinguishes this tool from siblings like list_subscriptions, which likely lists subscriptions rather than alerts. It also names the returned entities (source, citation_uri, raw payload), removing any ambiguity.

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 explicit usage context: filtering by type and/or since, using mark_read for read-state management, and confirms polling is acceptable. It even points to an alternative raw endpoint for scripts/dashboards, though it 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.