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

Annotations already flag destructiveHint=true, but the description goes well beyond them: it warns the next deploy drops their data, documents all-or-nothing atomicity ('refuses them all, naming it, and nothing is saved'), and discloses the 409 refusal on a stale expected_version. It also names the response fields ('applied', 'diff', 'plan', 'version') that no output schema provides.

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 destructive warning is front-loaded, then operations, then refusal behavior, then workflow, each as a distinct labeled block. It is longer than a one-liner but no sentence is redundant against the annotations or schema.

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 mutation with no output schema, the description supplies the missing return-value information, the atomicity guarantees, the failure mode, and the surrounding workflow. Nothing an agent needs to invoke it safely and correctly is absent.

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 the baseline is 3, but the description lifts it by giving concrete operation payloads (drop_table/drop_field JSON examples) and by restating the atomic in-order application and the expected_version refusal semantics. This adds usable format detail beyond the schema's generic 'items: object'.

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 ('Drop tables or fields from a project's saved schema') and immediately disambiguates scope with '(saves to database, does NOT deploy)', separating it from the deploy_* siblings. An agent can distinguish it from patch_schema, update_schema, and deploy_destructive without opening any 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?

Provides an explicit numbered workflow (preview_schema_change -> drop_schema_items -> deploy_staging/deploy_destructive -> get_job_status) that names the alternatives and the condition selecting each one. It also states when to pass expected_version and what happens if someone else saved meanwhile.

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