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

Against annotations that only declare readOnly=false, destructive=false, idempotent=false, openWorld=false, the description adds substantial context: the plan expires, nothing is dispatched or purchased, raw configuration and credentials are never returned, grants and permissions are required, and ineligible/foreign/unapproved sources 'fail closed.' It also discloses the key semantic caveat that a queued successor counts as local success only while provider results remain unverified.

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?

The purpose is front-loaded, but the body is a dense run-on of fragments and repetition, notably the redundant 'Requires OAuth store:imports:resume consent. Requires separate store:imports:resume consent' and the ambiguous sentence 'A strict expiring plan or durable source-to-successor receipt.' Several clauses could be consolidated without losing information.

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?

For a two-parameter planning tool with an output schema and annotations, this leaves little unanswered: approval binding, consent scopes, fail-closed conditions, non-actions, and the local-vs-provider success distinction are all covered. An agent has enough to decide whether to call it and what to expect from 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%, so the baseline is 3, but the description adds constraints the schema lacks: the source must be owned, FAILED or CANCELLED, no older than 30 days, with at most 100 remaining items, and exactly one source per plan. It reinforces rather than contradicts the expected_version rule that changed checkpoints require a new review.

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 first sentence states a specific verb and resource: 'Persist a frozen local resume-only plan for one exact owned FAILED or CANCELLED import job and version.' It separates itself from execution siblings by negation ('never creates a successor, dispatches a worker or calls a provider'), but it never names supercatch_execute_import_resume as the tool that consumes the plan, leaving the prepare/execute split to be inferred.

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?

Eligibility is spelled out concretely: FAILED or CANCELLED CSV_IMPORT / INDIVIDUAL job, no older than 30 days, at most 100 remaining items, AI recognition disabled, and 'inspect and approve the exact plan in SuperCatch first.' It also gives recovery guidance ('recover the original operation with its original key after a lost response'), but the follow-on execution step is described only as generic approval rather than by naming the sibling tool.

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