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

Annotations only say readOnly=false and destructive=false, so the description carries the interesting behavior: redeploy reuses the last successful deploy's repo/folder/branch and the project-stored env, a CONFLICT signals an in-flight deploy, and the compute alternative 'replaces the running server' when given settings. That is real context beyond the annotations. It stops short of saying what the call returns (a deploy id?) or how long a rebuild typically takes, which is the kind of detail needed to poll sensibly.

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-loaded with the core action and the minimal invocation, then the polling/CONFLICT rule, then the compute exclusions – a sensible priority order with no filler. The middle clauses are dense and run long ('with that id redeploys it (same branch — pushed code included — folder, size, port, env, mounts)'), which costs a little readability.

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?

Given no output schema, the description still tells the agent the call is asynchronous (poll get_status) and enumerates the sibling routing decisions an agent is most likely to confuse. The remaining gap is the return value of redeploy itself and how to observe completion or failure beyond get_status, which a fully complete definition for an async mutation would include.

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 already 80% and documents the env/branch/subdir defaulting behavior, and the description reinforces it ('Call it with just projectId', the same repo/folder/branch are reused). The branch rule for names containing '/' is schema-provided rather than repeated, so the description adds alignment with the no-arg invocation model rather than new per-parameter syntax.

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 ('Redeploy a web-hosting project from its latest repo state') and immediately scopes it by noting the rebuild reuses the last successful deploy's repo, folder, branch and stored env. This lets an agent distinguish it from the compute siblings named later in the description without opening any 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?

Explicit routing guidance: 'Call it with just projectId', poll lavela.get_status (CONFLICT means one is already running), and an explicit exclusion 'NOT for a server on compute' that points to lavela.compute_build_status / lavela.compute_rebuild, plus when provision_compute_from_repo applies (first deploy or confirmed settings). Both when-to-use and when-not-to-use are covered with named alternatives.

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