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

Goes well beyond the lone destructiveHint=false annotation: discloses an access restriction (internal staff only), a state override the caller cannot control ('Everything starts at Sourced regardless of what you pass'), duplicate existence, and the GitLab exclusion that would otherwise produce a bad row. These are exactly the side effects an agent needs before writing.

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 scope rule and the staff-only gate, then the ICP, then the data-quality rules. Every sentence carries information, though the prose is slightly long for a create tool and the 'nobody can act on later' justification is editorial padding.

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 12-parameter create tool with full schema coverage, minimal annotations and no output schema, the description covers audience, qualification criteria, dedupe ordering, state behaviour and data-quality expectations. Missing only what the call returns on success or on a duplicate hit, which is a modest gap given 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 100%, so the baseline is 3; the description earns above that by adding intent beyond the field docs — signal must be why-now, source_url must be recheckable, qualification_needed is where unverified facts go rather than guessing. The only gap is that priority (A/B/C) and next_action get no extra guidance.

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 (add a company or adviser to the outbound pipeline) and immediately scopes it to a specific ICP (CTO/head of engineering/hands-on EM at a 10–30 engineer product company on GitHub or Bitbucket, no GitLab). That is enough to distinguish it from save-prospect-draft-tool, update-prospect-tool and get-prospect-worklist-tool without opening any schema.

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?

Explicitly gates the tool to internal Coderbuds staff, tells the agent to de-duplicate with get-prospect-worklist first, and prescribes what to put in signal/source_url versus qualification_needed instead of guessing. It even gives a negative example ('looked like a fit') so the agent knows a low-quality invocation when it writes one.

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