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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=true, and openWorldHint=true. The description adds meaningful behavioral context beyond those flags: it requires an enabled retention policy, it does not ingest or approve, and it clarifies that the original remains unchanged while future filling creates a separate version. This is useful behavioral disclosure, though it could have added a bit more about failure modes or side effects.

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 description is three sentences with no filler. The core action and constraint are front-loaded, followed by exclusions and a clarifying note about versioning. Every sentence earns 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 7-parameter mutation with no output schema, the description covers the critical context: what counts as a valid input, what the tool does not do, and the retention-policy prerequisite. It does not describe the response shape or error conditions, but the absence of an output schema and the presence of strong parameter-level descriptions in the schema make this acceptable. A small gap remains around what happens on success or failure.

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 29%, so the description carries meaningful weight. It clarifies that projectId is a Helvabase project/mapping ID and never a local path, and that idempotencyKey must be reused exactly after a timeout. The description also reinforces that contentBase64 must be actual bytes, not invented ones. It does not explain every parameter, but the schema already provides patterns and constraints for most, and the description adds the most safety-critical semantics.

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 states a specific verb ('Store actual bytes'), a precise resource ('one explicitly selected, manifest-authorized production original'), and a hard constraint (max 1 MiB). It also distinguishes itself from related operations by explicitly saying it does not ingest or approve the file, which helps an agent separate it from siblings like helvabase_upload_sources or helvabase_add_evidence_version.

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 description gives explicit when-to-use guidance: only for a manifest-authorized production original, only when a retention policy is enabled, and never with a local path or invented bytes. It also states what the tool does not do ('does not ingest or approve the file'), which is a clear exclusion that prevents misuse.

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