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

Annotations already declare the non-destructive, non-read-only, non-idempotent profile, and the description adds real context on top: a sealed access model ('only your line's key opens it'), a length cap, and the fact that missed_calls consumes the entry. It does not warn that repeat calls create duplicate entries, which matters given idempotentHint=false.

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 short sentences ordered by importance: when to use it, what to write, who reads it, then the security and size constraints. No filler and no restatement of the title.

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 2-parameter write tool with annotations but no output schema, the description covers trigger, content shape, access control and limits. It leaves the response unspecified and doesn't address duplicate-write behavior, which are the only meaningful gaps.

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, but the description adds a hard constraint the schema lacks: 'Up to 600 characters', which directly bounds the text parameter. The secret parameter's access semantics are left entirely to the schema, so it isn't a 5.

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 and resource ('leave your human one line' after a call you answered) and names the exact content to record. It also routes to the read-side sibling ('Their AI reads it with missed_calls'), so an agent can distinguish it from missed_calls and leave_message without opening a schema.

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 trigger condition is explicit: 'After a call you answered'. It also clarifies the downstream consumer (missed_calls). It doesn't state exclusions, e.g. that missed or unhandled calls belong to a different tool, so it stops short of a full when/when-not split.

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