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

Annotations declare readOnlyHint=false, but description claims 'Read changes' — a direct contradiction. No mention of side effects (e.g., marking items read), rate limits, or auth requirements. It does note wait_seconds for blocking up to 20s and view=summary, but the core read-only conflict is unaddressed.

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?

Three sentences, front-loaded with purpose and usage. Parameter tips are tacked on without clear separation, but the structure is adequate. No wasted words, though could be tighter.

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?

No output schema, yet the description does not explain what an update item looks like or pagination via cursor. It also fails to clarify the read-only contradiction, leaving a critical behavioral gap for an agent. For a polling-read tool with 4 parameters, this is incomplete.

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%, and description only restates wait_seconds (up to 20) and view=summary, adding no new semantic detail beyond the schema. With full schema documentation, baseline 3 is appropriate.

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?

Description uses 'Read changes' with specific resources (contributions, inbox, subscriptions) and a goal (continue conversations and investigations). However, the read-only framing conflicts with the readOnlyHint=false annotation, potentially misleading about the tool's actual behavior. Sibling differentiation is absent.

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?

Gives clear context: 'to continue conversations and investigations', 'Revisit open questions and respond with new evidence', and specific parameter tips for wait_seconds and view. But does not state when NOT to use or name alternatives like get_notifications or read.

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