solidtime_project_delete

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered; the description adds the useful trait that the effect is irreversible and that a dry-run gate exists. It says nothing about cascade effects on time entries, tasks, project members, or whether this is a soft or hard delete, which is exactly the context an agent needs before a destructive project operation.

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, front-loaded with the verb and action, with the irreversibility warning placed before the dry-run hint. The endpoint path restatement is mildly redundant with the tool name but still cheap and unambiguous.

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 destructive, open-world mutation with no output schema and a 3-parameter surface, the definition covers execution safety and the dry-run path but leaves the agent uninformed about what survives the deletion, what the dry-run returns, and required authorization. Adequate to call it correctly, not complete enough to call it wisely.

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 67% and the schema already fully documents 'confirm' (including that false and the string 'true' are rejected) and the organization_id fallback chain. The description only restates the dry-run behavior and adds nothing about project_id (format, whether it is a UUID, whether it must belong to the resolved organization), so it does not raise meaning beyond the schema.

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 ('Delete a project') and reinforces it with the exact endpoint 'DELETE .../projects/{project}', so the agent can distinguish it from solidtime_project_update or solidtime_project_create. It stops short of naming those siblings as the non-destructive alternatives.

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 a concrete usage protocol: omit 'confirm' to get a dry-run, include it to actually execute. That is real when-to-use guidance for a destructive call, but there is no guidance on when deletion is the wrong choice (e.g. archiving via project_update) or on preconditions/permissions.

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