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

There is a direct annotation contradiction: annotations mark readOnlyHint:true, but the description explicitly describes mutation via 'Set mark_read:true to flag returned events read so the next call only shows newer ones.' This is a state-changing operation, conflicting with read-only semantics. The idempotentHint is also questionable when mark_read is used repeatedly. Such contradictions confuse the agent about side effects.

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, each earning its place: the first states the core function, the second details return contents, and the third covers filtering, mark_read, polling, and an alternative endpoint. It is compact, front-loaded, and contains no fluff.

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?

The description covers the return payload (source, citation_uri, raw event payload), filtering options, mark_read side effects, polling suitability, and an external endpoint. No output schema exists, so the description carries the burden of explaining return values, which it does. However, the contradiction with readOnlyHint leaves a completeness gap regarding side effects, though the description itself is fairly comprehensive.

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% with descriptions for all five parameters. The description adds value by providing an example for type ('sec_8k'), clarifying since as 'ISO timestamp,' and explaining the broader effect of mark_read: 'so the next call only shows newer ones.' It also mentions the return payload fields, though those are not parameters. This goes beyond the schema's basic 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 starts with 'Pull fired events from your subscription feed,' which clearly identifies the verb (pull) and resource (subscription feed/alerts). It also distinguishes itself from sibling tools like list_subscriptions and subscribe by focusing on retrieving fired events.

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 for use: filtering by type/since, setting mark_read for polling new events, and noting that 'Polls work fine.' It also suggests an alternative for scripts/dashboards via 'GET registry.pipeworx.io/alerts.json.' It does not explicitly exclude other use cases or name sibling alternatives, but the guidance is clear.

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