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

Goes well beyond destructiveHint=true: it discloses retention semantics (notes, files, activity kept; prospect re-addable), that mail always ends regardless of cascade, that cascade=false preserves memberships/opportunities, that user approval and confirmed=true are prerequisites, and that writes are never auto-retried. These are exactly the consequences an agent needs before a destructive call.

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 action and archiving behavior, then prerequisites. Slightly repetitive — 'end its mail' and later 'Mail always ends' say the same thing, costing one clause.

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, non-idempotent mutation with no output schema, it covers effect, reversibility, data retention, cascade option, approval gate, and retry policy. Nothing material is missing for correct invocation, aside from what a success response looks like, which is minor given no output schema.

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 only 33% (the `cascade` query param has no schema description), and the description compensates by explaining precisely what cascade=false preserves. It also reinforces the `confirmed` approval gate already documented in the schema. Minor gap: it presents cascade as `?cascade=false` while the schema types it as a string, so an agent gets no guidance on accepted literal values.

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 ('Remove prospect', 'Archive the prospect') and immediately clarifies that this is a reversible archive rather than a hard delete. That framing distinguishes it from the granular sibling deletes (files, notes, photos, tags) under the same prospect.

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?

Gives clear conditions: use this to remove/archive a prospect, pass `?cascade=false` to preserve list memberships and open opportunities, and the user must approve before calling. No explicit exclusions pointing at an alternative tool (e.g. update vs. remove), but the context is unambiguous enough for correct selection.

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