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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds real value beyond that by delimiting the blast radius: 'The companies and their public records are not affected' and pointing to the Memory page for other profile edits. It doesn't confirm irreversibility or partial-failure behavior, keeping it from a 5.

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 main action is front-loaded in the first clause, and every sentence carries information. However, the first sentence is long and packs mode definitions into a dense parenthetical, which slows parsing slightly.

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 3-parameter mutation tool with no output schema and covered annotations, this is close to complete: it describes each mode, what is and isn't destroyed, and a prerequisite lookup via account. Only the return/confirmation behavior and handling of partial vs. full deletion are unaddressed.

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 the baseline is 3, but the description goes further by explaining the distinct effect of each parameter: companies clears status and removes from all profile lists, stop_working only removes from prospects, watches deletes by name. That nuance is not in the schema descriptions.

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 uses a concrete verb (deletes) on a named resource (what Whimbrel keeps for this rep about a company) and then spells out three distinct modes: companies, stop_working, watches. It does not explicitly contrast itself with siblings like remember, but the per-mode breakdown makes the tool's scope unambiguous once read.

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 states the triggering condition ('when the rep asks') and gives an explicit fallback: 'If the rep did not give the exact name, read their watches from account first,' which routes the agent to a sibling tool. It stops short of stating when not to use this tool (e.g., use remember to add instead).

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