Apply a Solution Configuration

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

Annotations only declare destructive/not-readOnly/not-idempotent; the description goes well beyond by disclosing dual writes to the DB and the git-tracked sidecar (with sidecarPath and a commit recommendation), refusal-before-write semantics for malformed or locked sidecars, a warning path when the file becomes unreadable mid-write, and keep-rule relocations between 'exclusions' and 'keepNamespaces'. It also states validation behavior (invalid matchType rejected, non-boolean keep flag rejected).

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?

The first sentence front-loads the action well, but the remainder is one very long unbroken paragraph mixing core behavior, JSON examples, and edge-case error handling. Some JSON example content duplicates what the schema property descriptions already show for testProposalJson, so a portion of the text does not earn its place.

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 destructive, dual-target write tool with nine parameters and no output schema, the description covers what an agent needs: what gets created and activated, where it is written, the returned sidecarPath, the commit obligation, and the failure modes that abort or partially succeed. The remaining gaps (naming parameters, layeringPolicy) are fully carried by the schema.

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 100%, so a 3 is the baseline, but the description genuinely adds meaning the schema lacks: literal JSON shapes for proposalJson and testProposalJson, the matchType value set (Contains|StartsWith|EndsWith|Exact) even though no schema enum exists, the fact that test rules match PROJECT names, and the keep/keepNamespaces semantics. Only the naming parameters (layerProfileName, exclusionListName) and layeringPolicy get no extra treatment.

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 resource: it applies a proposed layer/exclusion/test configuration and creates plus activates the corresponding profiles and sidecar entries. The scope (DB + git-tracked <SolutionName>.aicb.json, slots marked initialized) is concrete. It never names a sibling such as init_solution_config or check_solution_config_drift to draw the boundary explicitly, so it falls 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?

It gives operational rules for using the tool correctly (at least one axis must be non-empty, testPreset is mutually exclusive with testProposalJson, an axis not named retains the existing sidecar value), which implies when it is applicable. However, it never says when to prefer this over siblings like init_solution_config or solution_config_status, nor does it state prerequisites or exclusions relative to alternatives. Usage is inferable but not routed.

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