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

Annotations already provide readOnlyHint=true, and the description does not contradict that. It adds valuable context about what the report contains (client-facing, assembled from setup-time data), how lockedSections behaves (names sections absent until a research run), and the rendering options (markdown vs structured fields). While it doesn't discuss errors or performance, the behavioral profile is well-covered beyond the 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?

The description is longer than average but every sentence contributes: purpose first, then free/availability, then rendering details, then lockedSections, then the alternative. It is efficiently front-loaded with the core message and avoids redundant filler, though it could be trimmed slightly without losing key facts. Overall it is well-structured and information-dense.

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 getter tool with a single parameter and no output schema, the description is thorough: it explains the report's content, its availability, what lockedSections means, and how the rendered output differs from structured data. The only minor gap is the lack of an explicit note about response shape (e.g., whether the markdown is a string or a file), but the description's mention of 'ready-to-send render' sufficiently covers it. Given the simplicity of the tool, completeness is high.

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%—the lone parameter projectId has no description in the schema, and the tool description does not mention it at all. However, the schema itself provides a strict UUID format and pattern, making the parameter self-explanatory for a tool named 'get_starting_point_report'. Because the parameter is trivial and the schema is authoritative, the description's omission does not cause confusion, but it also adds no semantic value, so a baseline 3 is appropriate.

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 ('Get') and a precise resource ('the free starting-point report for a project'), then elaborates on what the report contains (positioning, site inventory, competitor set, rising-topic signals). It explicitly names the sibling tool (get_pitch_report_payload) and the condition that selects it ('prefer get_pitch_report_payload: that is the full report'), leaving no ambiguity about which tool to call.

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?

It states the tool is 'Free on every plan, no research run required,' and gives a clear when-not-to-use instruction: 'Once the project has a completed run, prefer get_pitch_report_payload: that is the full report.' This directly addresses when to use this tool versus the alternative, fulfilling the guidelines dimension completely.

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