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

The annotation readOnlyHint=true claims the tool does not modify state, but the description says setting mark_read:true flags events as read and affects subsequent calls — a state-changing side effect. This directly contradicts the read-only annotation, so per the rubric transparency must be 1 and this is an annotation contradiction.

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 dense sentences, front-loaded with the core purpose and containing no filler. The HTTP mirror note earns its place as a practical integration detail for scripts and dashboards.

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 compensates by explaining that returned events carry source, citation_uri, and raw payload, and by covering filtering and mark_read semantics. It leaves limit and unread_only to the schema, which is acceptable, but a bit more detail on ordering or default behavior would make it fully complete.

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?

All five parameters have 100% schema coverage, so the baseline is 3. The description goes beyond the schema by giving a type example ('sec_8k'), clarifying 'since' as an ISO timestamp, and explaining the semantic consequence of mark_read. This operational context adds real value.

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 opening phrase 'Pull fired events from your subscription feed' gives a specific verb+resource and clearly identifies the tool's domain. It differentiates itself from siblings like list_subscriptions and recent_changes by explaining that it returns alert events with source, citation_uri, and raw payload.

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 states filtering by type and/or since, and explicitly says 'Polls work fine', giving clear context for repeated calls. It also names the HTTP mirror for scripts/dashboards, which is a useful alternative. It does not explicitly contrast with sibling tools, so it falls just short of a 5.

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