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

Beyond the annotations (readOnly=false, idempotent=false, destructive=false), it adds the required purchase_orders:write scope and a meaningful semantic fact: linking does not affect committed cost. It doesn't disclose duplicate-link behavior or error conditions, but it substantially enriches the behavioral picture.

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 tight sentences, front-loading the primary action, then auth/requirements, then the cost-vs-link caveat. No redundant restatement of the title or schema.

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?

With no output schema and full annotation/schema coverage, the description supplies the constraints and cost semantics an agent needs. It only omits the return/duplicate-link behavior, which is a minor gap for a link-creation call.

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 already 100%, so the baseline is 3, but the description adds the mutual-exclusion constraint ("exactly one of" the three target IDs) that the schema itself does not enforce. That is genuine semantic value above the schema and the per-parameter descriptions.

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 ("Link") and resource ("a purchase order") with the set of valid targets (work order, PM schedule, project). It clearly distinguishes itself from create_purchase_order and create_purchase_order_line by being a pure association operation.

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?

Gives the key selection rule ("exactly one of work_order_id, pm_schedule_id, project_id") and an important when/when-not distinction ("A link does not add to committed cost; to charge the cost, set project_id or work_order_id on the purchase order itself"). It does not name sibling alternatives like update_purchase_order or the delete/get/list link tools, so it falls short of full alternative routing.

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