prepare_form_row_candidate

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

The only annotation is readOnlyHint=true, so the description carries most of the behavioral burden. It usefully discloses that conflict checks against both baseline and target are performed, and the phrase 'local candidate' signals that the remote environment is not touched, which is what reconciles the write-sounding verb with readOnlyHint. It does not say what happens when a hash mismatch is detected (abort, error, overwrite) or whether repeated calls are idempotent.

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?

A single front-loaded sentence with the verb and object up front and no filler. It is arguably too terse given the tool's complexity, but nothing in it is wasted or buried.

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?

Eleven parameters, ten required, a mutation of local candidate state, no output schema and near-zero schema coverage make this a complex tool, and one sentence cannot cover it. The agent is not told what the call returns, how conflicts are surfaced, or what the ordering constraints are relative to capture_form_baseline and the publish/apply tools.

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 9%: only environment_profile is documented, leaving ten required parameters (baseline, source, target and their three hashes, section_id, cell_id, action, row_hash) with no explanation anywhere. The description adds nothing about how the three hash triples relate to the three snapshot strings or how row_hash is computed, so it fails to 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?

The description supplies a specific verb pair (add or remove) and a precise resource (one reviewed row in a local candidate), so the agent knows the unit of work is a single form row and that the edit lands in a staging candidate rather than the live environment. It does not name or differentiate itself against the many adjacent prepare_*_candidate siblings (prepare_form_node_candidate, prepare_component_candidate, prepare_form_candidate), which keeps it short of a 5.

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?

There is no statement of when to choose this tool over the sibling candidate tools, nor of the prerequisites implied by the parameter set (a captured baseline, a prior inspect_form_row, an existing candidate). The word 'reviewed' hints that a review step must precede the call, but the agent is left to infer it from the adjective alone.

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