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

Annotations already declare readOnlyHint=true, but the description adds meaningful behavioral context: it is a no-research-run report, markdown is the ready-to-send render, structured fields are for custom rendering, and lockedSections lists sections that are absent here rather than previewed. This goes beyond the annotation and gives the agent a clear model of what the tool returns and what it intentionally does not include.

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?

Every sentence earns its place: definition, availability, render semantics, the meaning of lockedSections, and sibling routing. It is front-loaded with the core purpose and remains dense without being padded.

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?

Even with no output schema, the description tells the agent what data the report contains (positioning, content inventory, competitor set, rising-topic signals), what markdown versus structured fields mean, and what lockedSections represents. It also covers the one important decision point—when to use get_pitch_report_payload instead. The required parameters are documented in the schema, so the description does not need to repeat them.

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 50% because the context parameter has a description but projectId only has format/pattern constraints. The tool description never mentions either parameter by name; "for a project" only weakly maps to projectId, and the required context parameter's meaning is left entirely to the schema. With medium coverage, the description should have added explicit parameter semantics but does not.

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 opens with a specific verb and resource: "Get the free starting-point report for a project," and immediately explains what this report is (a client-facing document assembled from setup-time data). It explicitly differentiates itself from the sibling get_pitch_report_payload, saying "prefer get_pitch_report_payload: that is the full report," so an agent can tell them apart.

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 gives explicit when-to-use guidance: "Free on every plan, no research run required" and "Once the project has a completed run, prefer get_pitch_report_payload." This clearly states the condition for choosing this tool versus the alternative and leaves nothing to inference.

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