save_project_artifacts

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

Beyond annotations (which are all false hints), the description adds that the operation is a persist operation on non-secret artifacts and that it returns a content hash and resource URI. It does not disclose details about overwriting, storage behavior, authorization needs, or artifact size limits, so there is still a meaningful transparency gap.

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 a single sentence with no redundant wording. It front-loads the core purpose and then adds the return behavior, earning its place with every phrase.

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 two-parameter tool with an output schema, the description is minimally viable: it says what to persist and what will be returned. Still, it leaves the artifacts object format unspecified and omits any operational context like whether artifacts are replaced, merged, or versioned. This is adequate but has clear gaps.

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 0%, so the description must carry parameter semantics. It broadly indicates that 'artifacts' are generated and non-secret, but it does not define the structure of the artifacts object, what values it may contain, or clarify project_id beyond the property name. This is insufficient for low schema coverage.

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 uses a specific verb ('Persist') with a clear resource ('generated non-secret project artifacts') and states the return value ('content hash and resource URI'). It clearly distinguishes this tool from the sibling analysis, validation, and generation tools by framing it as a storage/persistence operation.

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 signals when to use the tool: for generated artifacts that are non-secret. It implicitly excludes secret artifacts and manual/non-generated artifacts, which gives solid context. However, it does not name an alternative tool or explicitly state when-not-to-use relative to a sibling.

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