Delimit Substantive Content Check

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

The description explicitly claims 'Side effects: read-only. Pure validator... no network, no ledger writes, no notifications,' while the annotations declare readOnlyHint: false. This is a direct contradiction: the annotation signals the tool may have write/network effects, but the description insists it is a pure read-only validator. An agent cannot trust the safety profile, which is critical before invoking a pre-submit gate. Flagged as Annotation Contradiction.

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 long, but it is well-structured with clearly labeled sections (when to use, when not, sibling contrast, side effects, two stages) and front-loads the purpose. The two-stage explanation is detailed and somewhat documentation-like, so not every sentence is lean, but the complexity of the gate justifies most of the length.

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 complex policy gate, the description covers the two veto stages, the side-effect profile, mandatory-usage context, and sibling interaction — essentially everything an agent needs to invoke it correctly. The one caveat: the contradictory readOnlyHint annotation leaves the operational safety picture unresolved, which slightly undermines completeness despite the thorough prose. Output schema exists, so return-value documentation is not the description's burden.

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 100%, so the baseline is 3. The description adds genuine meaning beyond the schema by explaining how parameters participate in the two-stage logic: repo/repo_description/repo_topics feed the 'target-side veto' and body feeds the 'content shape' checks, including the KYC/deanonymization rationale. This tells the agent WHY each parameter matters, not just what it is.

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 states a specific verb-and-resource purpose: 'Pre-submit gate for autonomous github outreach' that validates the substantive-content boundary. It explicitly distinguishes itself from the closest sibling: 'delimit_external_pr_check guards PR duplication; this guards the substantive-content boundary itself.' An agent can tell what this tool does and how it differs from delimit_external_pr_check without opening any schema.

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?

Provides explicit when-to-use ('as the LAST step before any agent submits a comment, issue body, or PR description to a third-party github repo via the outreach_substantive task path'), when-NOT-to-use ('for internal repo content, for posts on platforms other than github, or for non-outreach submissions'), mandatory policy context (CLAUDE.md SHIFT-1, founder-approval bypass), and call-ordering relative to delimit_external_pr_check. This is the gold standard for routing guidance.

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