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

Annotations already cover read-only/idempotent/non-destructive, so the description's added value is the workflow constraint and the `imports:write` scope requirement, both of which are genuinely beyond structured data. The scope line is notable for a list operation and worth flagging, but it does not contradict the annotations, which describe side effects rather than OAuth scopes. Minor gap: no mention of pagination limits or response shape.

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, zero filler, and the core operation is front-loaded before the caveat. Each sentence contributes something distinct: what it lists, what is unavailable, and what scope is required.

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?

There is no output schema, yet the description at least implies a jobIdentifier is part of a job record, which is the key field an agent needs to chain into pm_get_import_job. What is still missing is any hint of job status values or what pagination metadata comes back, which matters for a polling-style workflow.

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%, so page, pageSize, workspace, and account are already fully documented in the schema. The description adds no parameter detail — no default page size, no guidance on when to pass workspace versus the configured one. Baseline 3 is correct when the schema carries the whole burden.

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 with scope: 'List CSV import jobs for the current workspace, paginated.' An agent immediately knows what it returns. It stops short of naming pm_get_import_job as the single-job sibling, so sibling differentiation is only implied by 'come back here with the returned jobIdentifier.'

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?

Explicitly tells the agent what it cannot do here (CSV upload endpoints are multipart and not exposed) and prescribes the workaround: upload via a non-MCP client, then return with the jobIdentifier. That is real routing guidance. It never states the inverse case — use pm_get_import_job for a single job's status — so the alternative is inferred, not named.

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