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

Annotations already cover the write/safety profile (readOnlyHint=false, idempotentHint=false), but the description adds real context they don't carry: the note lands on the alert timeline, it is visible to the team, and it does not page anyone. It stops short of stating whether notes can be edited/deleted or what permissions are needed, which is why it isn't a 5.

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?

Two short sentences plus the route, front-loaded with the WRITE marker so the mutation nature is the first thing read. No filler sentences.

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 sensibly covers what happens to the note rather than a return payload. Combined with annotations, an agent has enough to call this correctly; only permission requirements and reversibility are left unstated.

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 alert_id, user_id and text are already fully documented, including where to obtain the ids. The description only echoes the path parameter naming (signlId) and adds no format or constraint detail beyond the schema — the baseline 3.

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?

Opens with 'WRITE: add a text note to an alert's timeline' — a specific verb, resource and effect. It is trivially separable from read-side siblings like signl4_get_alert_timeline, and the POST path reinforces the action.

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?

'It does not page anyone by itself' implicitly contrasts this with paging siblings such as signl4_raise_alert, and 'on behalf of a SIGNL4 user' hints at attribution requirements. However, there is no explicit statement of when to choose annotate over raise_alert or ack, nor any exclusions or prerequisites.

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