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 description's job is to say what destruction means — and it does: status is cleared, entries are removed from named firm-profile lists, while 'the companies and their public records are not affected.' It also points to the Memory page for the rest of the profile, which is real routing context. It does not say what happens when a listed company isn't present, or whether the action is confirmed/undoable.

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-loaded with the verb and what is destroyed, then the mode split, then the non-effects. One dense paragraph with no filler, though the nested parentheticals (status, then three list names) make it slightly harder to parse than a bulleted split would be.

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 two-optional-parameter destructive tool with no output schema, the description covers the essential unknowns: what is deleted, what is untouched, and which surfaces are affected. Remaining gaps are small — whether both arrays can be supplied together and what the response reports — but nothing that would cause a wrong invocation.

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 genuine meaning: `companies` is described as writing status (client / not a fit) and removing from three specific lists, while `stop_working` is scoped to the prospect list only — a distinction the terse schema descriptions ('profile entries' vs 'the rep's accounts') leave ambiguous.

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 ('Deletes what Whimbrel keeps for this rep about a company') and immediately splits it into the two distinct modes the schema exposes (companies vs stop_working). It does not explicitly contrast with the inverse sibling `remember`, so it stops short of full sibling differentiation.

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 a clear trigger ('when the rep asks') and, more usefully, states the selection rule between the two parameters: `companies` clears status and profile lists, `stop_working` only removes from the prospect list. It never says when to prefer another tool, such as re-adding a company via `remember`, so exclusions are absent.

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