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

Annotations already signal destructiveHint=true (alerting to damage) and idempotentHint=true (unusual for deletion but noted). The description adds crucial behavioral context beyond annotations: it explicitly lists what gets destroyed ('all deployments, the managed PostgreSQL database, environment variables, and webhooks'), states the action is 'PERMANENT and irreversible', and mentions that 'The project slug will become available again after deletion.' This goes well beyond what annotations alone convey.

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?

The description is two sentences long, front-loads the action and permanence, and lists the destroyed resources concisely. Every sentence serves a purpose: first sentence states the action and its finality, second sentence details what is removed and the side effect. Zero waste.

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?

Given the tool's high complexity (destructive, irreversible, many side effects), the description is complete: it specifies what is deleted, that it's permanent, and that the slug becomes available again. There is no output schema, and the description does not need to explain return values for a deletion tool—the important information is the outcome, which is clearly stated.

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 coverage is 100% with a single parameter (project_id) already documented as 'Project ID (UUID) to delete. Use list-projects to find the ID.' The description does not add new parameter semantics, but since coverage is high and the parameter is simple, the baseline is 3. The description earns a 4 because it provides important usage context (where to get the ID and what happens upon deletion) that complements the schema without being redundant.

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 clearly states 'Delete a project and all its deployments from sota.io' with a specific verb ('Delete'), resource ('project and all its deployments'), and platform ('sota.io'). It distinguishes itself from siblings like list-projects, create-project, and set-env by describing the permanent and irreversible nature of the action.

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?

The description indicates when to use it (to delete a project) and highlights its permanence and irreversibility, guiding the agent to be cautious. However, it does not explicitly state when not to use it or provide alternatives among sibling tools (e.g., consider archiving or using rollback instead). The strong emphasis on permanence implies rare use, but no exclusions are given.

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