SDLC Evidence Packet

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint), yet the description goes well beyond them: repository text is untrusted, caller assertions are recorded unverified, and high-confidence prompt injection is stripped from the Markdown channel while the structured packet retains it. That trust-boundary and sanitization disclosure is exactly the kind of context annotations cannot carry.

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?

Three sentences, front-loaded with the action and scope, followed by the two trust rules. Each sentence carries distinct information and none is padding.

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?

An output schema exists, so return-value description is unnecessary, and the annotations plus the trust-model sentences give an agent enough to call it safely. The only real gap is the absence of any routing guidance among the many sibling packet/triage tools, which is a usage rather than a completeness defect.

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 description coverage is 100%, so the schema already documents the subject union and the callerAssertions field, including 'Always recorded as unverified'. The description restates that trust stance but adds no syntax, format, or fallback detail (e.g. nothing on repo/owner env fallback beyond what the schema says). Baseline 3 is appropriate where the schema does the heavy lifting.

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?

States a specific verb and artifact ('Generate a versioned, read-only evidence packet') and constrains the subject to exactly one Issue, pull request, or release ref. The purpose is unambiguous on its own, but it never contrasts itself with near-neighbours such as agent_handoff_packet or repo_context, so an agent must infer which packet-producing sibling applies.

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?

Usage is implied by the subject constraint ('one Issue, pull request, or release ref'), which tells the agent the input shape but not the situation that calls for this tool. No when-to-use, when-not-to-use, or named alternative from the sibling list appears in the description.

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