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

Annotations already include idempotentHint and destructiveHint, and the description adds that no outreach/import/merge occurs and bind fields are rejected. However, it does not explicitly state that no persistent changes are made or describe what result is returned, which is significant for a preview tool; the readOnlyHint is false, adding ambiguity.

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?

One sentence, front-loaded with the core purpose and scoped with exclusions. No redundant words.

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?

The tool has 6 parameters and no output schema, but the description doesn't state what a preview result looks like, how errors occur, or whether any state changes happen. It leaves the agent to infer too much for correct 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?

With 0% schema description coverage, the description was expected to compensate, but it only hints at prospect_id and job_posting_id via 'Prospect' and 'Application'. It does not explain note, request_id, source_label, or idempotency_key, nor what 'bind fields' refers to.

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 clearly states the action ('Preview conversion'), the resource ('one Prospect into one canonical Application'), and distinguishes from binding by noting 'bind fields are rejected'. This is specific and allows an agent to differentiate it from convert_bind and other preview tools.

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 the tool is for non-destructive preview before binding, but it does not explicitly name the alternative (convert_bind) or state when to use preview vs bind. No exclusion conditions are given beyond 'bind fields rejected', so usage guidance is only implied.

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