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

The description directly contradicts the readOnlyHint annotation. It says 'Set mark_read:true to flag returned events read so the next call only shows newer ones,' which is a state-changing operation, while readOnlyHint=true implies no persistent modifications. This is a severe inconsistency that undermines the agent's trust in the tool's safety profile. No other behavioral traits are disclosed beyond this conflicting mark_read behavior.

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 but information-dense. It front-loads the main purpose, then provides return structure, filtering options, read-state behavior, and an alternative access method. Every sentence earns its place, with no redundant or vague statements. It is well-structured for quick parsing.

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?

Given there is no output schema, the description adequately explains what the return payload contains (source, citation_uri, raw event payload). It covers filtering, since timestamp, mark_read behavior, and alternative access for scripts. Despite the contradiction, the description alone is complete for usage purposes, though the contradiction slightly undermines overall completeness.

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%, but the description adds meaningful context beyond the schema. It gives a concrete example for the 'type' parameter (e.g. 'sec_8k') and explains the consequence of setting mark_read:true ('so the next call only shows newer ones'). This enhances the agent's understanding of parameter behavior beyond the bare schema descriptions, so it exceeds the baseline 3.

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's purpose with a specific verb and resource: 'Pull fired events from your subscription feed.' It further distinguishes the tool by explaining it returns alerts written by the evaluator, which differentiates it from sibling tools like list_subscriptions or subscribe. The inclusion of return field details (source, citation_uri, raw payload) reinforces the purpose.

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 useful usage context: it explains polling works fine and points to an alternative REST endpoint for scripts and dashboards, implying when to use this tool versus an external alternative. However, it does not explicitly name or exclude sibling tools, so it falls short of a 5. The guidance on mark_read and filtering gives clear situational usage.

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