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

Goes well beyond the annotations: it distinguishes Staged changes (undoable until the next deploy) from immediate ones (template, autoDeploy, waitForCi, watchPaths, preferredBuilder) that cannot be undone that way, and says the result lists them under immediate. It also discloses that secret values never pass through this call and that no human approval is requested. This is exactly the kind of behavior an agent needs before a mutation.

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, then the patch semantics, then the staging caveat, then the secret rule, with no filler sentences. It is dense as a single unbroken paragraph covering several distinct concerns, which makes scanning harder than it needs to be, but every sentence carries information.

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 9-parameter mutation tool with nested objects and no output schema, the description covers the highest-risk aspects: reversibility, immediate effects, and secret handling. Gaps remain around optimistic concurrency (expect_revision) and the rename/reference-update interplay, both of which the schema documents but the description never surfaces.

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 89%, so the baseline is 3, but the description adds real meaning: set is a patch that keeps unnamed Settings, env inside set sets only the variables it names, and five named parameters have immediate, non-undoable effect. It does not explain expect_revision concurrency or the rename_env/update_references interaction, leaving those to the schema.

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: change one Service's Settings and variables in one step. It also draws the boundary against domain_update and config tools by saying domains are not Settings and are not changed here. An agent can tell exactly what this mutates without opening the 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?

Clear context on when this applies, plus exclusions ('Domains are not Settings and are not changed here') that implicitly route the agent elsewhere. It also notes secrets must go through generate_secret rather than being passed here. It does not name sibling tools such as service_rename explicitly, so routing is inferred rather than stated.

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