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

Annotations only supply readOnlyHint=false and destructiveHint=true; the description adds substantive semantics beyond that — partial-patch behavior ('only the fields you pass change'), blank-string handling that avoids accidental clearing, name-uniqueness refusal, and rename safety because purchase orders store the id. It stops short of stating auth/permission requirements or the response shape, which is the only reason it isn't 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?

Five tight sentences, front-loaded with the core action and immediately followed by the most error-prone semantics (patch behavior, blank handling). Every sentence carries information; the name-related content is split across two sentences but neither is filler.

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 12-parameter mutation with 8% schema coverage and no output schema, the description covers the semantics an agent most needs: partial update, blank handling, uniqueness conflict, and the cross-sibling boundary for costs. Return values aren't required without an output schema. Remaining omissions are per-field expectations and auth requirements.

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 only 8% (just supplierId documents 'id from get_suppliers — not a name'), so the description must compensate for 11 undocumented fields. It explains the update semantics (passed vs. omitted, blank ignored) but never describes what individual fields like contactEmail or postCode expect or constrain. Field names are largely self-descriptive, so the gap is tolerable but real.

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 states a specific verb and resource with singular scope: 'Change one supplier's details.' It also distinguishes itself from a close sibling by explicitly carving out item-cost changes to link_supplier_items. The only minor gap is that 'details' is elaborated only later, but the boundaries are clear enough to route without opening a 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 an explicit when-not with a named alternative: 'This does NOT change item costs... use link_supplier_items to re-price.' That is a concrete routing rule. It doesn't address other near-neighbors (e.g., create_supplier, delete_supplier) or prerequisites like permissions, but the primary alternative is covered.

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