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

With no annotations, the description carries the full burden, and it does disclose meaningful behavioral facts: the record is signed, includes an attestation envelope for citation, and full=true can exceed 100K characters for deep reviews. It omits permissions/auth requirements and error behavior, but the payload-size warning is genuine context an agent needs before invoking.

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?

Two sentences, purpose front-loaded, and the enumerated return contents are compressed into a single readable clause. The only minor cost is the dense list of returned artifacts, but nothing is redundant or 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?

No output schema exists, so the description does the work of describing return contents and the full-record variant, which it handles convincingly. The remaining gap is the undocumented slug parameter and the absence of any guidance about sibling tools that return overlapping subsets.

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 compensate. It does explain 'full' thoroughly (adds data sources and the primary-data snapshot, much larger response), but the required 'slug' parameter is never described in either the schema or the description, leaving its format and source undocumented.

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?

Opens with a specific verb+resource ('One project's assessment') and immediately scopes it to a single project, which distinguishes it from compare_projects. It enumerates the exact payload (dual scores, breakdowns, integrity level, verdict counts, findings, review_url, attestation envelope) so an agent knows precisely what it gets back.

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 the full=true/full=false tradeoff well, including the payload-size consequence, but never states when to pick this tool over siblings like get_integrity_verdicts, get_freedom_breakdown, or get_returns_breakdown, which appear to return sub-portions of the same data. Usage is implied by scope ('one project') rather than spelled out.

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