prepare_composite_form_candidate

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

The annotations already declare readOnlyHint=true, and the description usefully reinforces this with "No CRM writes or packaging", clarifying the tool stops at local staging. It says nothing about the behavior that matters for a 7-required-parameter combinator: whether steps apply in order, whether baseline/source/target hashes are validated for drift, or what happens on hash mismatch. Adds some value over annotations but leaves the risky semantics opaque.

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, zero filler, with the positive action first and the scope exclusion second. Every clause carries information an agent needs.

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 tool with a deep nested steps schema, seven required parameters, no output schema and only a readOnlyHint annotation, the description is far too thin: it omits hash semantics, step ordering, and failure modes. Its one strength — the explicit no-write/no-package boundary — is important but not sufficient for an agent to call this correctly.

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 only 13% — only environment_profile is documented, while baseline, source, target, the three hashes, and the nested steps oneOf are bare. The description's "multiple ... form changes" loosely maps to steps and "local candidate" to the baseline/source/target triple, but it never explains that the hashes are content fingerprints used to pin the reviewed state, nor how the four step kinds differ. It does not compensate for the coverage gap.

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 and outcome: combine reviewed form changes into one local candidate, with an explicit scope boundary (no CRM writes or packaging). An agent can tell it produces a local artifact rather than applying anything. It does not name the singular siblings (prepare_form_candidate, prepare_component_candidate, prepare_form_node_candidate) that an agent would need to distinguish it from.

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?

"Explicitly reviewed" implies a prerequisite that the constituent changes must already have passed a review step (e.g. review_form_three_way / review_component_three_way), which is useful implied guidance. However, there is no explicit when-to-use versus the per-node/per-component prepare_* siblings, and no statement of when to prefer those instead.

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