Prepare Guard Review

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

With no annotations, the description carries the full disclosure burden. It says the packet is 'bounded' (consistent with the max_diff_chars cap) but never says whether the call is read-only, whether it writes a packet to disk, whether it invokes a model, whether it requires an initialized guard state, or what happens on a dirty/empty diff.

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 no filler. It is dense with undefined domain jargon ('project model', 'contracts', 'deterministic findings'), but nothing is redundant.

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 5-parameter tool with no output schema, no annotations, and 40% schema coverage, the description should say what the packet looks like when returned (structured object? file path? text blob?) and how it feeds the reviewer. That return-shape information is entirely absent.

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 40%, so the description must compensate: 'current diff' loosely points at base/max_diff_chars and 'project model' at root, and 'bounded' hints at the size cap. The 'requirement', 'changed_only', and all defaults/bounds remain unexplained, so the compensation is partial.

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 ('Prepare') and artifact ('bounded semantic-review packet') plus an enumeration of its contents, so an agent knows what it produces. It never distinguishes itself from close siblings such as codapult_guard_context, codapult_guard_analyze, or codapult_guard_check, which likely also assemble diff/model data.

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 only usage hint is the trailing phrase 'for an AI reviewer,' which vaguely implies a preparatory workflow step. There is no statement of when to call this versus the 13 sibling guard tools, no prerequisites (e.g. must guard_init have run first), and no exclusions.

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