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

The description states that setting mark_read:true will 'flag returned events read so the next call only shows newer ones,' implying a persistent state change. This directly contradicts the annotation readOnlyHint=true. The description adds useful behavioral context, but the contradiction is a critical flaw, making transparency score 1.

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 four sentences, effectively front-loaded with the main purpose, followed by useful details about return payload, filtering, mark_read, and an HTTP alternative. The HTTP sentence is slightly tangential but still concise and relevant.

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, filtering, mark_read behavior, polling suitability, and an alternative access method. Combined with the detailed schema, it provides a fairly complete picture for a read-oriented tool, though the mark_read contradiction is a significant gap that prevents a higher score.

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 the baseline is 3. The description adds an example for type ('sec_8k') and clarifies the consequence of mark_read on subsequent calls, which goes beyond the schema's descriptions. This enriches parameter meaning.

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 identifies the tool as fetching 'fired events from your subscription feed' and specifies what is returned (recent alerts with source, citation_uri, and raw event payload). This distinct verb+resource combination differentiates it from sibling tools like list_subscriptions.

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?

It explains how to filter by type and since, and provides contexts where polling is appropriate. The mention of the same feed via HTTP serves as an alternative for scripts/dashboards, giving clear usage context. However, it does not explicitly state when not to use this tool or contrast it with specific sibling tools.

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