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

Annotations declare readOnlyHint=true, but the description explicitly states that setting mark_read:true flags events as read and makes the next call show only newer ones. This is a clear state-changing behavior, directly contradicting the read-only annotation. This is an annotation contradiction, forcing a score of 1 despite otherwise transparent disclosures.

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 a compact, front-loaded paragraph. It begins with the main purpose, then covers filtering, mark_read behavior, polling, and an alternative access method. It is slightly longer than necessary but each sentence provides useful information without major 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?

For a read-oriented tool with five optional parameters and no output schema, the description covers what is returned (source, citation_uri, payload), filtering options, mark_read state effects, and even an HTTP mirror. It omits some edge details like limit specifics, but those are covered in the schema. The main gap is that the mark_read side effect is not reconciled with the readOnlyHint annotation.

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 description coverage is 100%, so all parameters are documented. The description adds extra value by giving a concrete filter example ('sec_8k'), explaining the effect of mark_read, and referencing ISO timestamps for since. This goes beyond the schema's basic parameter 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's purpose: 'Pull fired events from your subscription feed,' and specifies what each event carries (source, citation_uri, raw payload). It distinguishes itself from siblings like list_subscriptions and recent_changes by focusing on fired alerts with read-state tracking.

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 gives concrete usage context: filters by type and/or since, mark_read for stateful polling, and notes that polling works fine. It also names an alternative HTTP endpoint for scripts/dashboards. However, it does not explicitly mention when not to use this tool versus 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.