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

The annotation declares readOnlyHint:true, but the description explicitly says 'Set mark_read:true to flag returned events read', which is a state-mutating behavior. This directly contradicts the read-only annotation, so the description fails to align with structured metadata.

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 three sentences, front-loaded with the main action. Each sentence adds unique value: return payload/filters/mark_read/polling/alternative endpoint. No redundant or filler text.

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?

Without an output schema, the description compensates by explaining the return item fields (source, citation_uri, raw payload), filters, the mark_read side-effect, and polling feasibility. It also covers an alternative access method, making the description complete for practical use.

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 adds value beyond the schema by giving a concrete example for type ('sec_8k'), clarifying that 'since' is an ISO timestamp, and explaining the semantic effect of mark_read on subsequent calls.

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 'Pull fired events from your subscription feed' and specifies it returns recent alerts with source, citation_uri, and raw payload. This distinguishes it from sibling tools like recent_changes or list_subscriptions by focusing on subscription alerts.

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: polling is fine, and an alternative HTTP endpoint is mentioned for scripts/dashboards. However, it does not explicitly exclude sibling tools or state when not to use this tool, so it lacks full when-not guidance.

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