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

Announces WRITE, states irreversibility ('Cannot be undone through this server'), discloses the permission precondition, and explains downstream consequences (PO sent to supplier, invoice to payment). This adds real value beyond the destructive/readOnly annotations. Doesn't detail rate limits or the exact response, so not a 5.

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?

Front-loads 'WRITE:' and packs prerequisite, side effects, discovery path, irreversibility, and endpoint into tight sentences with no waste.

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?

Covers the important behavioral context (permission requirement, spending release, irreversibility) needed to call a mutation tool safely. No output schema exists, so return values needn't be explained; remaining gaps are minor.

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 schema already documents both parameters (idn as company document number, document as enum). The description adds no format or syntax details beyond it, making baseline 3 correct.

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 (approve) and resource (document), with the wire endpoint POST /{document}/{idn}/approve. It is clearly distinguishable from reject_document and submit_document siblings.

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?

Tells the agent where to find candidates ('list tools and waiting_for_my_approval') and states the precondition (user must be a current approver). It doesn't explicitly route to reject_document/submit_document for the alternative decision, so not a full 5.

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