scf_update_system

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the description's 'write' label partially overlaps with structured data. However, it adds genuinely new behavioral context: the editor+ role requirement and the crucial partial-update (PATCH-like) semantics in 'only provided fields are applied' — a behavior no annotation conveys. It does not contradict the annotations; readOnlyHint=false is consistent with 'write' and destructiveHint=false with 'update'.

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?

Two sentences totaling roughly 17 words, with zero filler. The first sentence front-loads the verb, resource, and role; the second delivers the essential parameter-behavior rule. Every clause earns its place, and no information is repeated from the schema or annotations.

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 10-parameter update tool with full schema coverage, strong annotations, and no nested objects, the description covers the critical semantics: the operation, the role gate, and partial-application behavior. The main gap is the absence of any return-value indication — there is no output schema, so an agent must infer what the tool returns; a note on the response shape or error behavior (e.g., 404 for unknown system_id) would complete the picture.

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 descriptions are unusually rich — they include cross-references like 'obtain from scf_list_systems' and preference guidance like 'prefer vendor_id'. The baseline is therefore 3, but the description's 'All fields are optional; only provided fields are applied' adds operation-wide parameter semantics that the per-field schema entries cannot express, clarifying that omitted means unchanged rather than cleared.

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 uses a specific verb-resource pair — 'Update an existing system record' — making the operation unambiguous. The qualifier 'existing' implicitly distinguishes it from the sibling scf_create_system, and the resource scope ('system record') separates it from update tools for other resources (vendors, evidence, engagements). It doesn't explicitly name the create alternative, so it stops just short of full sibling differentiation.

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?

The description provides clear usage context: this tool targets existing system records (not creation), requires an editor+ role, and applies only provided fields — which tells an agent exactly how to conduct an update session. It states the prerequisite (editor+ role) that the MID calibration example lacked. It does not explicitly route to alternatives like scf_create_system, but the context is clear enough that an agent won't misuse it.

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