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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, yet the description adds genuinely useful context beyond them: required store:listings:publish scopes, current EDIT_LISTINGS preconditions, fail-closed behavior on foreign/stale targets, non-disclosure of credentials and approval secrets, and no retry semantics. Against that value, the "Publish one exact eligible owned listing..." sentence reads as write behavior inside a read-only tool and forces the agent to reconcile it with the later "Read-only; never stages, approves, publishes or retries." The disclosure is rich but internally strained.

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?

Nine dense sentences for a one-parameter read tool, and the structure is not front-loaded around the read purpose: the second sentence describes publishing before the reader is told this tool is read-only. Consent, exclusion lists and recovery guidance are packed together with no separation of what the tool does versus what the surrounding workflow does. Useful facts are present but buried in a wall of negation.

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 values need not be explained, and the description does cover preconditions, consent, fail-closed behavior and recovery. What it does not do is state plainly the tool's role in the prepare/inspect/execute sequence, which is the main thing an agent needs to sequence calls correctly. Coverage is broad but the sequencing gap matters for a plan-inspection 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?

The single plan_id parameter already has a full schema description ("Exact publication plan ID returned by preparation") at 100% coverage. The description reinforces that the original key must be reused after a timeout, which adds a small amount of meaning about key provenance. It does not define format or sourcing beyond the schema, so baseline 3 applies.

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, "Read the frozen destination, price, quantity and native staging approval without provider writes," names a concrete read verb and the exact fields inspected. But the very next sentence, "Publish one exact eligible owned listing to one explicitly selected eBay export connection...," describes the publish flow rather than this tool, leaving the agent to disambiguate the tool's actual scope. It never names prepare_publication or execute_publication as the sibling that creates or consumes the plan, so differentiation is left implicit.

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?

There is real situational guidance: "After a timeout or lost response, inspect the original operation with its original key; never create a replacement intent to bypass uncertainty," which tells the agent exactly when to reach for this tool. However, it never states the entry condition (plan obtained from preparation) or routes the agent to execute_publication for the actual publish step. Usage is implied through the consent and fail-closed sentences rather than stated as when/when-not.

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