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

Beyond the annotations, it discloses two important behaviors: file bytes are not stored (only a reference/hash/metadata), and human verification is a separate step. That materially clarifies what this non-read-only mutation actually commits. It still omits duplicate handling for a non-idempotent write and the purpose of confirm_store.

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?

Three short sentences with zero filler; the primary action is front-loaded and the two key caveats (no file bytes, separate human verification) follow immediately.

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?

The behavioral side is reasonably covered for a mutation tool with no output schema, but with 0% schema coverage on 8 params and a required confirm_store gate, an agent still lacks the guidance needed to construct a valid call confidently.

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% across 8 parameters, including nested metadata, the sha256 pattern, project_key length bounds, and the required confirm_store flag. The description adds no parameter-level meaning at all, leaving the agent to infer everything from field names and enums.

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: 'Append a ... evidence reference/status/hash/metadata record to Project Workspace.' It clearly distinguishes a write-side evidence record from read-side siblings like abiyar_search_evidence or workspace_get_project, though it never names those siblings explicitly.

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?

'Human verification is separate' implies this tool should not be used to record human sign-off, but the description never says when to call this versus workspace_review_readiness or the quote-handoff tools. No prerequisites (e.g., the confirm_store requirement) are stated, so usage is only implied.

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