prepare_form_candidate

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

readOnlyHint=true already tells the agent this is a safe read; the description reinforces it with 'Does not write or package', which usefully confirms no server-side mutation or packaging occurs. However, it never clarifies what a 'local candidate' actually is, whether it is persisted or returned for a later apply step, or how hash mismatches are handled.

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 tight sentences with the core action front-loaded and the no-side-effect clause immediately after. No filler, though the brevity edges toward under-specification for an eight-parameter tool.

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 seven required parameters, a low-coverage schema, no output schema, and a densely populated sibling family, the description is too thin. It omits hash-verification semantics, what the candidate is consumed by, and any failure behavior, leaving real gaps an agent would need to guess at.

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%, so the description must carry more weight, and it does partially: it maps to target XML, the three hash parameters, and the 'explicitly selected supported attributes' that become operations. It adds nothing about the baseline/source XML parameters or the element/id/attribute structure within each operation, leaving several required inputs unexplained.

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 concrete verb and resource: 'Construct a local candidate from target XML' with a stated input basis (selected supported attributes, reviewed hashes). It implicitly separates itself from the many sibling prepare_* tools by targeting a whole form rather than a node, row, or component, though it never names those siblings explicitly.

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?

Usage is only implied: 'reviewed baseline/source/target hashes' suggests a prerequisite workflow step (hashes must be captured and reviewed first), and 'Does not write or package' hints that a separate apply/publish step follows. There is no explicit statement of when to use this versus prepare_form_node_candidate, prepare_form_row_candidate, or prepare_composite_form_candidate.

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