novel_continuity_check

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

With no annotations, the description carries the full burden and does well: it discloses mutual exclusivity of the three modes, that chapter mode also emits styleCandidates for forbidden words and speechStyle norms, and that the returned checklist enumerates covered and uncovered blind spots ('0 candidates' does not mean no problem). It does not state read-only vs mutation behavior, but for an audit tool the intent is clear.

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-loads the primary audit purpose and then the mode-specific behavior; no sentence is wasted. It is dense and uses heavy parenthetical/asterisk notation, which costs some readability but not correctness.

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 5-parameter tool with no annotations and no output schema, the description supplies the missing pieces: mode semantics, the styleCandidates return field, and the checklist blind-spot reporting. Return-shape coverage compensates for the absent output schema; only the read/write nature is left implicit.

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 100%, so baseline is 3, but the description adds a constraint the schema does not state: outline and ooc are mutually exclusive sentinel modes, and chapter mode additionally triggers style scanning placed in styleCandidates. That is genuine added meaning beyond the per-parameter schema text.

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: a coherence audit that scans the whole book against the settings table and emits contradiction candidates (number discrepancies, character absence, aliases, etc.). It carves out per-mode behavior (chapter / outline / ooc) so an agent can distinguish its modes from sibling analysis tools.

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?

Clearly explains that passing chapter triggers continuity auditing against the previous chapter, and that outline and ooc are independent sentinel modes that are mutually exclusive with it. It stops short of contrasting itself with overlapping siblings such as novel_style_check or novel_diagnose, which would complete the routing guidance.

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