SmartProspect: fetch contacts for a filter (consumes credits)

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

Beyond annotations (readOnlyHint=false, destructiveHint=false), the description discloses critical non-obvious behaviors: credit consumption, remote state modification, email sending capability (no), credit preflight check with rejection (never silent reduction), and no automatic retries. The safety breakdown explicitly echoes and expands on the annotations without contradiction.

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 description is structured into clear sections: purpose, credit warning, safety breakdown, endpoint, parameter constraints, and behavioral guarantees. Each sentence adds meaningful information, though the safety breakdown somewhat restates what the annotations and title already convey. Still, it remains focused and front-loaded.

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 credit-consuming mutation tool with 7 parameters and an output schema, the description is exceptionally complete. It covers the endpoint, authentication requirement, prerequisites, parameter relationships, credit preflight behavior, and error handling (rejects rather than reduces). The presence of an output schema means return value details are not required, and the description fills all other gaps.

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. The description adds value by emphasizing the mutual exclusivity of 'id' and 'limit' (also in schema) and by clarifying the documented limit range (1-10000, up to 30000 on some accounts), which goes beyond the schema's simple min/max. It also highlights the need for confirm_credit_spend=true, reinforcing the schema's description.

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 states a specific action ('Reveal contact email addresses') on a specific resource ('a saved filter'), with two distinct modes ('explicit adapt IDs' or 'bounded limit'). This clearly distinguishes it from sibling tools like smartprospect_search_contacts (search) and smartprospect_get_contacts (likely retrieving already fetched contacts).

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?

The description implies usage for a saved filter and provides clear prerequisites (SMARTLEAD_MCP_ALLOW_CREDIT_SPEND=true, confirm_credit_spend=true) and a mutual exclusion rule (id vs limit). However, it does not explicitly state when to prefer this tool over related tools like smartprospect_get_contacts or smartprospect_find_emails, nor does it provide 'when not to use' guidance.

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