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

Annotations already mark it as a non-read-only, non-destructive send. The description adds substantial context beyond that: any signed-in member of any account type can use it, the message must be in the member's own words with what they tried and what happened, the user must see and approve the message before sending, and a human replies by email.

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?

Front-loads the LAST RESORT constraint, then the alternative channel in parentheses, then eligibility, content requirements, approval flow, and outcome. Sentences are dense with useful information and none are wasted.

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 exists, and the description covers the full lifecycle: who may use it, when to use it versus alternatives, what to include, the required pre-send approval, and how the reply arrives. Nothing an agent needs to invoke it correctly is missing.

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 50%; the message parameter has a short schema description. The tool description adds meaningful content guidance for message (what they tried, what happened, which page or tool) and the pre-send confirmation process. The topic enum is self-explanatory but never mentioned, leaving one small gap.

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?

States a specific verb, 'send a message', and resource, 'ShearQuery's team'. It explicitly names the sibling send_shearquery_feedback as the channel for bug reports and feature ideas, so the agent can tell the two apart without inspecting schemas.

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?

Frames itself as the LAST RESORT after trying to help, names the alternative send_shearquery_feedback for bugs/ideas any time, and lists qualifying problems (account, billing, booking, unanswerable question). No ambiguity about when versus when not to use it.

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