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

With readOnlyHint=true already declaring the operation is non-mutating, the description adds behavioral context beyond the annotation: it defines fallback logic for the canonical name (operator-set, falling back to site brand then niche name), clarifies field semantics (`niche.name` is not the project name), and ties postsPerWeek to pitch report sizing. It does not dwell on return structure, which is acceptable since there is no output schema but the description already describes the key returned fields. This is a meaningful contribution beyond the annotation, so a 4 is warranted.

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 compact and information-dense: two sentences cover the resource, returned fields, a cross-reference to set_posting_cadence, and the critical `name` vs `niche.name` distinction. Every clause earns its place, and the most decision-relevant facts (what is returned and how to address the project) are front-loaded.

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 read-only fetch with two parameters and no output schema, the description conveys the key returned fields, the project-addressing convention, and the postsPerWeek/pitch-report relationship. It lacks an explicit statement about the `context` parameter's role or an explicit exclusion of sibling tools, but the definition is sufficient for an agent to correctly select and invoke the tool. Given the simplicity of the tool and the annotation coverage, this is a minor gap rather than a major omission.

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%: `context` is documented in the schema but `projectId` is not. The description compensates partially by clarifying which project field to use (`name` vs `niche.name`) and by explaining the meaning of `postsPerWeek`, but it does not explain the `context` parameter's intended input beyond what the schema already says. Since the description adds value beyond the schema for the semantics of the returned project data and clears a naming trap, it rises above the baseline 3, though it could have explicitly explained `context`.

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 'Get one project' and enumerates the specific fields returned: canonical name, niche profile, target audience, research status, and postsPerWeek. It also clarifies that the project is addressed by `name` and warns that `niche.name` is not the project name, which is a useful disambiguation. This clearly identifies the tool's resource and differentiates it from sibling tools like get_project_overview or get_research_status.

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 explains that postsPerWeek is the operator's publishing cadence and notes that it is settable via set_posting_cadence, implying when this read tool is relevant for sizing pitch reports. However, it does not explicitly state when to prefer this tool over sibling alternatives such as get_project_overview or get_starting_point_report, so exclusions are only implicit. That keeps it just below a 5.

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