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

Annotations declare it is not read-only, not destructive, not idempotent, but the description adds the crucial unannotated fact that each call burns community credits and describes the returned payload. It does not explain why a planning call is non-read-only, leaving a minor gap between the observed behavior and the readOnlyHint=false annotation.

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?

Four dense sentences, front-loaded with the core purpose and cost, then the return shape, then routing, then the parameter hint. Every sentence carries distinct information with no filler.

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?

With no output schema the description compensates by describing the return payload, and it covers cost and downstream handoff. The main shortfall is a documented 'intent' parameter and the 'language' field, but an agent can call this correctly overall.

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%, so the description must carry the parameter burden. It explains admin_language well ('the person's language so the plan and author_notes are written in it') and hints at question_count via 'up to 3 questions', but leaves intent and the language parameter undocumented, so half the parameters remain uninterpretable.

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 action ('Ask the AI what it would draft and what it needs to know') and enumerates exactly what comes back (outline, up to 3 questions with suggested answers, facts). It is clearly distinguished from the generate_script sibling, which it names as the downstream step.

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?

Explicit when/when-not ('Optional', 'Skip it when the request is already complete'), cost guidance ('spends a few hundred of the community's credits'), and a concrete workflow routing ('pass plan, answers and session_id to generate_script or create_project'). This is unusually complete routing for an agent.

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