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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered. The description adds one genuinely useful trait beyond that: the instructions use French UI labels, which affects how an agent presents them. It does not describe the return shape (text steps vs structured) even though no output schema exists.

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?

One front-loaded sentence with no filler; the parenthetical about French UI labels sits mid-sentence but is information-dense. Nothing needs to be cut.

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 simple read-only, single-enum-param tool this is close to sufficient, but with no output schema the description should say what the caller actually receives (a step list? per-client variants?) and whether the signature must already be generated.

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?

There is a single required 'client' parameter at 0% schema description coverage, but its seven-value enum is self-explanatory. The phrase 'in a given mail client' only loosely echoes the parameter and adds no format or constraint detail beyond the enum.

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+resource: it returns step-by-step install instructions for an HTML email signature, scoped to a mail client. This clearly separates it from generate_email_signature and the other siblings, though it never names an alternative explicitly.

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?

Usage is only implied — an agent can infer this follows signature generation and precedes manual installation — but the description never states when to call it, prerequisites (e.g. signature must already exist), or why you'd pick it over generate_email_signature.

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