sqo_pr_review

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

With no annotations provided, the description must carry behavioral disclosure, and it does add real value: a sub-65ms runtime expectation and a concrete output shape (GitHub PR Review Markdown table with 0–100 Grade A+). It omits whether the tool writes files, requires a git repo or network access, and whether runs are cached, which matter for an umbrella scanner with no annotations.

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 content is front-loaded into one sentence, which is efficient in length but heavily overstuffed: version strings, a codename ('Zenith'), and eight hyphenated gate names compete for attention. Trimming the branding and grouping the gates would make the operative information easier to parse.

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 usefully states the return format and grading scale. For a tool that orchestrates eight analyzers it still leaves gaps: it doesn't say what happens on failure, whether the report is persisted to disk, or whether thresholds/waivers are configurable.

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?

There is exactly one parameter with 100% schema description coverage ('Workspace root directory'), so the schema already fully documents it. The description adds no syntax, path-format, or scoping detail about the workspace beyond what the schema says, which is the expected baseline for full coverage.

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 names a specific resource (an 8-gate pre-PR/pre-deploy scorecard) and enumerates the actual checks it runs (SAST, FinOps, Council, N+1, RTL, phantom deps, env drift, secret DLP), so an agent can tell it apart from narrower siblings like sqo_council_review or sqo_finops_guard. The core verb is implied ('runs', 'outputs') rather than stated in an opening clause, and the marketing framing ('Autonomous', 'v13.0 Zenith') dilutes the signal.

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 'Pre-PR & Pre-Deploy' framing implies the usage moment, which is real guidance. However, it never states when NOT to use it or explicitly routes the agent to the single-gate siblings (e.g. use sqo_council_review alone for a quick council pass), so the selection decision is left to inference.

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