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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description goes well beyond them by disclosing side effects (people remain without a company link, delete_leads cascades to leads), irreversibility ('Cannot be undone'), and a required confirmation workflow. It also warns about the auto-relink quirk, which no structured field conveys.

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?

Front-loads the permanence and scope, then layers caveats; every sentence carries information. It is slightly dense and the trailing auto-relink note is tangential, but nothing is padding.

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, this covers safety, side effects, required preconditions, and the alternative tool. An agent has everything needed to call it correctly and only after explicit user consent.

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%, so baseline is 3, but the description adds real meaning: it explains delete_leads as a cascade that deletes the company's people too, and frames confirm as a post-approval authorization flag rather than just a boolean.

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 plus scope ('PERMANENTLY delete one CRM company') and immediately disambiguates from siblings by naming merge_crm_companies for duplicates. An agent can distinguish this from delete_crm_leads and delete_contacts 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?

Explicitly gates usage: only on the user's explicit request, show the company first via get_crm_company, then pass confirm: true after agreement. It also names the alternative tool for the duplicate case, so when-to-use and when-not-to-use are both covered.

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