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

The description explicitly states that setting mark_read:true will 'flag returned events read so the next call only shows newer ones,' which is a state mutation. However, the annotations declare readOnlyHint=true, implying no side effects. This contradicts the described behavior and is a serious inconsistency. The description itself is transparent about the mutation, but the annotation misleads the agent about the tool's side-effect profile.

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 appropriately sized with no filler. It leads with the core purpose, then covers return value, parameters, and usage context each in a sentence or two. Every sentence adds value, and the structure is easy to scan.

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 return value details, parameter usage, and even alternative access, which is good for a tool with no output schema. However, the contradiction with the readOnlyHint annotation creates confusion about side effects, and there is no mention of what happens with unread_only or limit defaults beyond the schema. The tool is complete in content but is undermined by the annotation mismatch.

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?

The schema already documents all parameters (100% coverage), but the description adds meaningful context: it gives an example for 'type' (sec_8k), explains the semantics of 'since' as an ISO timestamp, and clarifies the behavior of 'mark_read' and its effect on subsequent calls. This goes beyond simply restating parameter names and provides practical usage insight.

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 opens with a clear, specific verb-resource combination: 'Pull fired events from your subscription feed.' It goes on to specify the return value (source, citation_uri, raw event payload) and distinguishes itself from sibling tools like list_subscriptions or recent_changes by focusing on fired alerts in the feed.

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 context for usage, including it is for the persisted feed, supports filtering by type and since, and mentions that polling works fine. It also offers an alternative access method (GET registry.pipeworx.io/alerts.json) for scripts and dashboards, which implies when the tool might not be needed. It does not explicitly compare to other tools, 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.