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

Annotations only say non-read-only, idempotent, non-destructive; the description adds what the agent actually needs — write access required, admin-only escalation for run_via, silent floor-raising with the effective list reporting it, audit logging, and resource key. It even enumerates the response shape despite no output schema. Not a 5 only because error/rate-limit behavior is unaddressed.

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?

Dense but front-loaded: purpose first, then inheritance rule, then permission caveat, then response shape. Parenthetical task list and the quoted `unchanged` earn their place, though the response-shape sentence is long and partially duplicates what would be a return field listing.

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 by naming return fields, and it covers auth, inheritance, and idempotency well. It is less complete on what happens on failure — invalid model id, non-admin passing run_via, missing write access — which matters for a mutation tool with privilege tiers.

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 still adds value beyond it by explaining the inherit-vs-keep distinction between null/"" and omission, and by naming the semantic consequence of model choice (floor raising, effective list). It also spells out the run_via authorization dimension that the schema only hints at.

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 resource (set a pull request's AI model, covering review, risk summary, CI fixes, conflict proposals) and distinguishes it from siblings like merjax_set_ai_workspace_quota by scoping to a single PR's AI tasks. The null/"" inheritance semantics are named explicitly, so an agent knows exactly what the call sets.

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?

Gives explicit conditions: model id from catalog vs null/"" to inherit repo or platform choice; run_via requires a site-admin-scoped token and a repo a site admin owns. Omitted fields are kept and identical values return `unchanged`, which tells the agent when re-calling is harmless and which fields are optional.

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