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

The description genuinely adds risk context beyond the annotations: it confirms retained evidence can change, warns that a replacement operation risks duplication, and notes provider permissions govern disclosure. However, leading with "Reads" sits awkwardly against readOnlyHint=false/destructiveHint=true, so the mutation signal arrives late and diluted.

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 that are not front-loaded: the actual role of the tool never leads, and the most operationally important line ("a replacement operation risks duplication") is buried mid-paragraph in a semicolon-joined clause. Jargon crowds out the information an agent needs.

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 an output schema and rich annotations, the basics are covered, but for a destructive tool whose purpose overlaps several engineering_* siblings, the description never establishes its distinct role or what a safe call sequence looks like. An agent is left guessing at when this is the right tool.

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% and both parameters are fully documented with provenance hints, so baseline is 3. The word "scoped" loosely implies filtering by agent/conversation, but adds nothing the schema does not already say.

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 opening verb is "Reads" and the object is "scoped proposal/status projections," but "projections" and "reconciling automatic uncertain returned IDs" are unexplained internal jargon. An agent cannot tell what this returns or how it differs from near-neighbours like engineering_reconcile, engineering_resolve_unknown, or engineering_follow_ups.

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?

No sentence states when to call this versus alternatives. The warnings ("Unknown/submitting is not a created issue," "a replacement operation risks duplication") are state caveats, not selection guidance, and no sibling is named as the alternative path.

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