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

There is a direct contradiction with annotations. The annotations declare readOnlyHint=true and destructiveHint=false, which imply no persistent state changes. However, the description says 'Set mark_read:true to flag returned events read so the next call only shows newer ones,' indicating a mutation of persisted state. This contradicts the read-only annotation, so the score is 1 per the contradiction rule.

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 well-structured and front-loaded: it starts with the core purpose, then return contents, filtering options, mark_read behavior, and alternative access. Every sentence contributes value, with no redundancy or filler. It is appropriately sized for the tool's complexity.

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?

There is no output schema, but the description explains the return payload (source, citation_uri, raw event payload), covers the key filtering and state-change behaviors, notes that polling is safe, and points to an alternative GET endpoint. This provides comprehensive context for an agent to use the tool effectively, even without explicit return schema.

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 the baseline is 3. The description adds meaningful usage semantics beyond the schema: it gives a concrete example for type ('sec_8k'), specifies since as an ISO timestamp, and explains the behavioral effect of mark_read on subsequent calls. This enriches parameter understanding beyond field descriptions.

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 'Pull fired events from your subscription feed' and details the return contents (source, citation_uri, raw event payload). This distinguishes it from siblings like list_subscriptions, which manage subscriptions, and recent_changes, which likely handles different data. The verb 'Pull' and resource 'alerts' are specific.

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 clear context: it is for reading the persisted alert feed, filtering by type and since, and using mark_read to control read state. It also mentions polling is fine and points to an alternative HTTP endpoint. However, it does not explicitly exclude alternatives like recent_changes or list_subscriptions, so it lacks explicit when-not-to-use guidance.

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