aiworkhub_manager_skill_add_evidence

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

With no annotations, the description carries the full burden and does state the mutation shape (a row is appended), that invalid vocabulary is refused before a turn is spent, and the one mode where nothing is written. It omits permissions/auth prerequisites, idempotency (what happens on duplicate evidence), and whether the skill version must already exist.

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?

Front-loaded with the core action, then organized into vocabulary and identity sections. The canonical-form spelling example (manager.claude.7e vs claude_manager_7e) earns its place by preventing double-counted activations, but the prose is dense and slightly over-explained for an append operation.

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?

Output schema exists so return values needn't be explained, and the description covers the trickiest semantics (closed vocabularies, canonical identity equivalence, resolve mode). For an unannotated mutation tool it is nearly complete, missing only prerequisites and duplicate-append behavior.

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 0% across 7 params, so the description must compensate, and it does for the critical ones: the outcome vocabulary (accepted|negative), the actor_id regex and reserved role tokens, note as the required reason in resolve mode, and that source/outcome are ignored there. It leaves identity, version, and source's own format/meaning largely undocumented.

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 one MANAGER evidence entry to a skill version') with the added scope qualifier MANAGER WRITE. It distinguishes conceptually from card-derived evidence, but does not name a specific sibling tool (e.g. evidence_sweep or the task-derived path tool), so differentiation is only partial.

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?

Explicitly routes the agent: independent evidence comes from a card and is filed via the task-derived path, while this tool is for manager-filed entries. It also names the condition that switches behavior entirely ('When resolve_negative_source is set, no row is appended...'), which is exactly the kind of when/when-not guidance that prevents a wrong invocation.

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