assess_manuscript

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

With no annotations, the description carries the behavioral burden and does so well: it reveals that scaffold mode returns a prompt/schema/hash for the caller to execute, judge mode triggers a pinned-model API call requiring ANTHROPIC_API_KEY, and scoring is caller-independent. Minor gaps remain such as explicit side-effect/cost phrasing, but the core execution flow is disclosed.

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 front-loads the main purpose and then structures the two modes clearly. It is longer than average but each section adds behavioral or usage value, with no filler.

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 five-parameter tool with two distinct modes and a rich output schema, the description covers the overall flow and inter-tool dependencies well. It is incomplete on three parameters and does not explicitly describe the output schema's role, though an output schema exists to fill that gap.

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?

It gives strong semantics for the two most important parameters: document (path/raw text/text_sha256) and mode (scaffold vs judge). However, with schema description coverage at 0%, model, spec_version, and manuscript_id are left completely unexplained, so the description only partially compensates for the missing schema documentation.

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 first sentence states a specific action ('Assess a manuscript') against a defined scope ('all applicable TARGET leaves in one batched pass'), and the rest distinguishes the two execution modes. This sets it apart from siblings like parse_manuscript (ingestion) and submit_scaffold_verdicts (validation) without needing to open schemas.

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 explicitly maps scaffold mode to interactive LLM-in-the-loop review and judge mode to headless/batch corpus runs, and even advises that judge is 'overkill' for interactive review. It also names the follow-on tool submit_scaffold_verdicts and references parse_manuscript as the input source.

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