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

Annotations already declare readOnlyHint=true and destructiveHint=false, so 'Read only' is largely redundant. The description earns credit for going beyond them with domain behavior: labor from time cards counts toward actual cost, the breakdown granularity is per cost code with totals, and the auth requirement is stated. It does not cover pagination or large-project limits.

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 purpose, and the labor/auth caveats earn their place. There is mild redundancy — the second sentence restates the first sentence's enumeration of estimated/actual/difference before adding 'plus totals'.

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 read-only single-parameter report with no output schema, the description fully specifies what is returned (per-cost-code figures plus totals), how actual cost is derived, and the auth prerequisite. Nothing an agent needs to call it correctly is missing.

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?

With 100% schema coverage and a single documented parameter (project_id, sourced from list_projects), the schema carries the semantic load. The description's 'one project' framing reinforces but does not extend the parameter's meaning.

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 (get job costing) for a precisely scoped resource (one project), and enumerates the exact figures returned: estimated cost, actual cost and the difference per cost code. An agent can tell this apart from the sibling get_project and list_projects tools without opening a 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?

Usage is implied by 'for one project' and the schema's 'Project ID from list_projects' pointer, and it names a prerequisite (a Cotlet API key with app access). However, there is no explicit when-to-use vs alternatives statement or exclusion, leaving routing to inference.

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