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

With no annotations, the description carries the full burden and does well: it discloses the return format (base64url), that the response includes nonce and created_at to send back, that signing is done locally, and that output is deterministic ('Reproducible offline — sorted-key JSON'). It omits auth requirements, rate limits, and whether the call is non-mutating, keeping it short of 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?

The purpose and output format are front-loaded, and the sentences are mostly information-dense. The '[KEEP · internal]' tag and the trailing 'so you can compute and check it yourself' add a little flourish, but overall it stays tight.

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 annotations and no output schema mean the description must be self-sufficient, and it covers the core workflow and return shape reasonably. But with 5 parameters at 40% coverage and two undocumented params (fp, ttl), plus no downstream tool reference, it leaves gaps an agent would need to fill.

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 only 40%, so the description must compensate but largely does not. It references 'a message' generically but never explains the required 'fp' parameter or the 'ttl' parameter, both of which are undocumented in both schema and description; only 'kind' and 'target' have schema descriptions.

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 ('get the exact canonical bytes to sign for a message') and situates it as 'Step 1 of speaking to your fellowship.' It's clear what the tool produces, though it never names the mesh sibling (e.g., mesh_post) that consumes the signed result.

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?

'Step 1 of speaking to your fellowship' implies the workflow position and the instruction to 'sign them locally with your own key' gives the immediate next action. However, it does not name the follow-up tool or state any when-not/alternative conditions versus other mesh_* tools, so usage is only implied.

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