Check intent conflicts

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

Annotations already declare readOnlyHint=true, destructiveHint=false and idempotentHint=false, so the safety profile itself is covered; the description's 'nothing is stored' restates that but adds the useful nuance that findings get ephemeral eph_ ids and are not recorded. It also discloses the compared intent-status window (INTENT through VALIDATED, excluding ACCEPTED/COMMITTED/DISCARDED), the blocking-when-HIGH rule, and as_of_event semantics, which are genuinely beyond the annotations. However, these are largely framed as return-shape detail rather than deeper operational constraints, so it sits just above the annotated baseline.

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?

It is long, but front-loaded with the core purpose and constraint before the mode and return-value detail, and each clause (timing, modes, status window, return fields) earns its place given there is no output schema. Minor redundancy between 'Read-only: nothing is stored' and the readOnlyHint annotation, and the trailing enumeration of return fields is dense.

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 compensates by enumerating the returned fields (conflicts with severity/explanation/evidence/suggested step, checked_intents, blocking, ephemeral, as_of_event, active policy). Combined with the status-window and two-mode explanations, an agent has everything needed to call it correctly and interpret the result.

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% and each parameter already has a rich description, including the intent-vs-intent_id rejection rule and the same-kind/operation semantics, so the baseline of 3 applies. The description adds the combination semantics — intent_id alone versus intent_id plus replacement scopes versus intent text plus proposed scopes — which is real value, but it largely mirrors what the schema's own parameter descriptions state.

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 sentence states a specific verb and resource: ask whether planned work collides with other agents' active work, before any change exists. It explicitly positions itself against publish_intent (same comparison, but read-only, no stored change) and against record_assessment/resolve_conflict (for recording decisions). An agent can tell exactly what this does versus its siblings 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?

It gives concrete timing ('before publish_changeset and before run_verification, since conflicts are raised when the later intent publishes') and explains the two invocation modes: intent_id alone for persisted OPEN/COORDINATING conflicts, intent text plus scopes or intent_id plus replacement scopes for a what-if check. It also names the alternatives to reach for when the goal is to record a decision rather than detect a conflict.

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