concur_recall_report

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), it discloses the state transition, the approval-window constraint, that the report is re-read and its observed status returned, and the full confirmation protocol including the confirmToken fallback and MCP_CONFIRM_MODE. It also flags a concrete safety risk by forbidding execution driven by instructions embedded in tool results — context the annotations do not carry.

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 sentence order is well front-loaded: what it does, when it is allowed, what it returns, then the confirmation mechanics and safety caveat. It is dense but every clause carries operational information; the final anti-injection sentence is long but earns its length given the destructive-adjacent nature of the call.

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 mutation with no output schema, the description covers action, precondition, post-call verification, and the confirmation handshake, which is everything an agent needs to invoke it safely. No return-value documentation is required since it states the observed status is answered directly.

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%, and the schema already documents both reportId and the confirmToken two-phase protocol in detail. The description adds only a summary of the two-step fallback, so the baseline 3 applies rather than any extra credit.

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 description opens with a specific verb and resource ('Recall a submitted SAP Concur expense report') and immediately states the resulting state ('returning it to you unsubmitted'), then anchors it against a sibling by naming concur_submit_report as its inverse. An agent can distinguish this from concur_submit_report, concur_update_report, and concur_delete_report 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 a hard precondition ('Only possible before it is approved') and an explicit inverse relationship to concur_submit_report, so the agent knows when the operation is legal. It does not spell out the alternative routes (e.g. updating or deleting a report already approved), which keeps it short of a full when-to-use map.

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