rastermoves_info

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

Goes well beyond the annotations by disclosing that this is asynchronous ("Returns a retained background job") and must be polled, and that effects are not fixed but conditional on inference/download per danceflow_component. It also names the base effect flag ("write"), which matches readOnlyHint=false and destructiveHint=true. The remaining gap is that destructiveHint=true is never explained — what the write/destructive component actually touches is left to the component check.

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?

Four short, front-loaded clauses with no filler; the async-return warning and the sibling pointers come before any effect detail. The telegraphic phrasing ("Base effect flags: write", bare "poll danceflow_job_status") is dense but readable, costing a little clarity.

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 detail is not required, and the async/polling contract is covered. But this is a nested-object tool with a permissions gate and a destructive hint, and the description never explains the authorization relationship between permissions.write and the "write" effect flag, nor what cache_dir changes — material gaps for a destructive-classified 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?

With 50% schema coverage, the description does add one important constraint: the model must already be known locally, i.e. no implicit fetch occurs. However, cache_dir is never mentioned despite carrying an 8192-char bound, and the permissions object (whose schema text warns flags are "not independent authority") is only obliquely referenced via "Base effect flags: write", so the agent must infer that permissions.write must be acknowledged.

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?

Names a specific verb+resource ("Inspect one locally known model") and immediately scopes it against the catalogue family by stating it does so "without fetching catalogue or weights", which an agent can contrast with rastermoves_models/rastermoves_download. It stops short of naming the sibling to use for catalogue lookups, so the differentiation is implied rather than explicit.

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?

Implies the use case (pre-flight inspection of an already-present model) and gives two forward pointers: poll danceflow_job_status for the returned job, and check danceflow_component for conditional effects. It never states when *not* to use it (e.g. when the model is not local, or when rastermoves_models/rastermoves_doctor is the correct call), so selection guidance remains inferential.

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