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

Annotations already establish the write/non-destructive/non-idempotent profile, so the bar is lower. The description adds two useful behavioral facts not in the annotations — a key/credential is required, and the budget acts as a hard cap on what linked tenders may commit — but it says nothing about failure modes, what happens if budget is exceeded, or the response.

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?

Compact at roughly two sentences with no filler, but front-loading a conceptual definition of a project rather than the action wastes the most valuable position. The semicolon-chained clauses make it denser than it needs to be for three parameters.

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?

With 0% schema coverage, no output schema, and annotations covering only the safety profile, the description should explain the parameters, the key requirement concretely, and the creation outcome. It supplies domain color about projects but leaves an agent unable to confidently fill in title, currency, or budget_minor semantics.

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 0%, so the description must carry parameter meaning and it largely fails. It gestures at budget ('caps what all parts may commit') without clarifying that budget_minor is in minor units or how currency interacts, and the required 'title' parameter is never mentioned at all.

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?

The description explains what a project IS ('groups tenders under one budget') and implies creation via the project_id reference, but never states the action plainly ('creates a new project with a title and budget'). It does implicitly distinguish from get_project/post_tender by describing the grouping role, but the verb+resource framing is left to the tool 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?

'post the parts of a bigger job as tenders with project_id' sketches a usage pattern but only as a domain explanation, not as a when-to-use rule. Nothing tells the agent when to call create_project instead of set_budget, post_tender, or get_project, and 'Needs a key' is an unelaborated precondition rather than guidance.

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