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

Annotations already declare non-readOnly, non-idempotent, non-destructive, closed-world. The description adds two pieces of real value: an auth requirement ('Needs a key') and the budget-cap semantic (the budget bounds the sum of all committed parts). It omits what happens on duplicate titles and whether the returned project id is needed for the project_id reference it mentions.

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 clauses with no wasted filler, but it is front-loaded with domain explanation rather than the action, and the semicolon-chained phrasing is denser than needed for a create tool.

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 small 3-param create tool with full schema coverage and no output schema, the definition covers the concept, the auth requirement, and the budget semantics. The main gap is not hinting that the created project yields an identifier the agent needs before referencing project_id on tenders — minor but relevant to the described workflow.

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 title, currency, and budget_minor are fully documented in the schema. The description only echoes the budget concept without adding format or constraint detail beyond it; 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?

The description explains what a project *is* (a budget grouping for tenders) but never states the action — 'creates a project' is only implied by the tool name. It distinguishes the concept from siblings implicitly (project_id ties tenders together) but never names a sibling like post_tender or set_budget.

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?

It implies usage ('post the parts of a bigger job as tenders with project_id'), which tells the agent why a project exists, but gives no explicit when-to-use vs. when-not or which sibling handles the follow-up steps (post_tender, set_budget, get_project).

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