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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so safety is partly covered; the description still adds real value by spelling out the side effects (company record, contact with name/title/email/phone, prospect tag, notes containing the fit rationale) and confirming existing prospects are untouched, plus that the call is free.

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?

Dense but front-loaded: the primary action and record contents come first, then the optional-parameter rule, then idempotency, then cost. No filler sentences; every clause carries information about behavior or arguments.

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-parameter mutation with no output schema, the description covers what is created, what happens on repeat calls, and the cost model. The one gap is the return value — it does not say what the call reports back (e.g., created company/contact IDs), which matters since no output schema exists.

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 50% — prospect_ids has no schema description — but the description compensates by explaining its omit-to-keep-all semantics, including batching across a whole search. search_id is documented in the schema as the call_id from prospects_find, so both parameters are covered between the two sources.

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 concrete verb and resource: adds prospects into the CRM as a company plus a contact/lead with named fields. It is clearly a write-to-CRM operation, distinguishable from read siblings like prospects_list or prospects_get, though it never names the sibling it pairs with (prospects_find) explicitly.

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?

'Leave prospect_ids out to keep all a search found' gives actionable usage guidance for the optional parameter, and 'Prospects kept before are left as they are' sets expectations on re-runs. However, it never says when to choose this over prospects_prepare or other siblings, or what preconditions (an existing completed search) are required.

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