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

The description discloses that setting mark_read:true modifies the read state of events, meaning subsequent calls only show newer entries. This contradicts the readOnlyHint=true annotation, which implies the tool is strictly read-only, creating an annotation contradiction. Thus the behavioral transparency is severely undermined.

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 long and front-loads the core purpose in the first phrase. Every sentence adds useful information without redundancy.

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 core return fields, filtering, and stateful behavior despite lacking an output schema. It also points to an HTTP endpoint for additional access. However, the contradiction in read-only status leaves some ambiguity that affects overall completeness.

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 describes each parameter, and the description adds concrete examples (e.g., filtering by type 'sec_8k' and ISO timestamps) and explains the effect of mark_read on future calls. This enriches the parameter semantics 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 clearly states the tool pulls fired events from the subscription feed, which is a specific action with a clear resource. It distinguishes itself from sibling tools like list_subscriptions by focusing on recent alert events, not the subscription list itself.

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 explains when to use the tool (to pull recent alerts), and provides guidance on filtering by type and time, as well as using mark_read to control future reads. It also mentions an alternative HTTP endpoint for scripts, though it doesn't explicitly contrast with sibling tools.

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