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

Annotations already cover the write/non-destructive/non-idempotent profile, so the description's added value is the uniqueness constraint (a server-side rejection condition) and the no-delete lifecycle fact, plus the REST endpoint. It stops short of saying what error/duplicate behaviour or permissions look like, but it meaningfully exceeds what annotations declare.

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?

Three short sentences with zero filler; the 'WRITE:' prefix front-loads the mutation nature, then purpose, then constraint, then lifecycle alternative.

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?

Covers mutation intent, uniqueness, and the no-delete follow-up path, which is what an agent needs to avoid a failed call. Minor gap: no output schema exists and the description does not indicate what is returned (e.g., new cost code id) for subsequent calls.

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%, including the uniqueness note on 'name' and the display_option enum semantics, so the schema carries the parameter burden. The description adds essentially nothing parameter-specific beyond repeating uniqueness, which matches the baseline 3.

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 a cost code') and immediately clarifies the domain concept ('phase or work activity that time can be booked against'). It also distinguishes itself from get/list/update siblings by naming the lifecycle tool (exaktime_update_cost_code) explicitly.

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 the essential precondition (name must be unique) and the lifecycle rule that deactivation is done via exaktime_update_cost_code because there is no delete. It does not explicitly contrast with list/get siblings, but for a create tool the when-to-use is effectively implied by the unique-name and no-delete guidance.

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