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

Annotations already declare read-only, idempotent, non-destructive behavior, so the safety profile is covered. The description adds real behavioral context beyond that: a link to the full guide is returned, and an unrecognized client yields a catalog of available guides instead of an error.

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 purpose in the first sentence, then adds invocation and fallback detail. The client-value enumeration is long but earns its place as the de facto enum for a schema that defines none.

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?

With no output schema, the description carries the return-value burden and does so by naming the steps and the guide link. Combined with the annotations and the fully documented single parameter, an agent has what it needs to call this correctly.

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 goes further by enumerating concrete valid client values (gmail, outlook-new, outlook-classic, apple-mail, ios-mail, zoho-mail, thunderbird) that the schema only sketches with two examples. That materially improves correct value selection.

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 (get install steps for adding an email signature) and scopes the source (Signatoro's install guides) plus the return value (steps with a link to the full guide). No sibling tool overlaps this purpose, so it is trivially distinguishable.

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?

Explains how to invoke it ('pass the app as client') and what happens for an invalid input ('an unknown client answers with the list of guides there are'), which covers the practical when/how. It does not name explicit alternatives, but no sibling tool provides install steps, so the routing job is done.

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