pitch

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

With no annotations, the description still discloses meaningful traits: it is a background (async) job, it mutates state by scoring the pitch and assigning lead scores to every person, and it requires a live environment. It does not explain how to retrieve the async result (job_status/results) or what happens if the simulation is not alive.

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 'Sales rehearsal' and the core action, and every clause adds information (precondition, rebuttal format, scoring outputs). The rebuttal-format parenthetical mid-sentence makes it slightly run-on, but there is little waste.

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 7-parameter mutation with no output schema and no annotations, the description covers the workflow and rebuttal shape but leaves the async retrieval path and four parameters unexplained. An agent knows what the tool does and roughly when, but not how to fully parameterize or collect its result.

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 0% across 7 parameters, so the description must carry the load. It documents rebuttals well ({objection_type: text, '*': generic}) and implies script and simulation_id, but run, channel, product, and segment get no explanation at all — over half the parameters remain opaque.

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: pitch a script to every simulated buyer of a simulation, collect objections, answer with rebuttals, and score the pitch plus each person. The full pipeline (pitch → objections → rebuttals → scoring) is unambiguous and distinct from siblings like market_test, which only sets up the simulation.

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 a concrete precondition: the environment must be alive, so either run market_test with rounds first or start it. That tells the agent when the tool is callable. It doesn't name alternatives for other scenarios (e.g. email_test or website_test for non-pitch rehearsals), so it stops short of full routing guidance.

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