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

Goes well beyond annotations (non-readonly, non-destructive, non-idempotent). States 'Nothing is deployed', explains what the returned plan contains (package, cluster, consumers, parameters, cluster room), how defaults resolve (region/data boundary from cluster policy or 'unspecified'; parameters from package), and the required permission.

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?

Two dense sentences plus a short permission note. Front-loads purpose, then the return/confirmation behavior, then defaults, then the human-review step. No filler.

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-param, mutation-like preparation tool with no output schema, the description covers purpose, return content, default resolution, absence of side effects, downstream dependency, and required permission. Everything an agent needs to invoke it 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 description coverage is 100%, so the schema already documents all 9 parameters in detail (including enums, UUIDs, and defaults). The description adds default-resolution semantics at a high level but does not provide per-parameter meaning beyond what the schema offers. Baseline 3 is appropriate.

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: 'Prepare the review of a new managed service' and identifies itself as 'step one of `ankra services setup`'. Clearly distinguishes it from the sibling confirm_service_setup by naming it as the tool whose digest this produces.

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 workflow guidance: it is 'step one', it returns a plan that confirm_service_setup needs, and it instructs 'Show the plan to the user before confirming'. Also discloses the permission prerequisite ('Requires applications.deploy').

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