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

Goes well beyond the annotations: the generated value is never revealed to anyone, the secret has no expiry and persists until a person deletes it, and the tool never accepts a caller-supplied value. It also explains the ${SECRET_SLOT:<id>} return contract and that resolution happens at deploy time.

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?

Four sentences, each doing distinct work: purpose, return contract, lifecycle, and alternative routing. Front-loaded with the core action and 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?

No output schema exists, but the description explains exactly what comes back (the sentinel) and how to use it. Combined with the lifecycle and value-generation rules, an agent has everything needed to invoke 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 description coverage is 100%, so name/length/prefix/description are already documented. The description reinforces that no value parameter exists ('It never takes a value') but adds no extra guidance on length bounds or prefix usage, so baseline 3 applies.

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 ('Create an organisation secret whose value Ankra generates') and immediately defines the narrow class of credentials it serves. It is clearly distinguished from the sibling that handles pre-existing values by name.

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?

Gives concrete when-to-use examples (database password, signing key, shared token) plus an explicit exclusion and alternative: 'for a secret the person already has, use request_secret.' No inference required.

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