continuity audit

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context by clarifying the division of labor ('supplies evidence; the assistant must identify contradictions') and that it does not mutate state ('Does not save or approve the scene'), but it says nothing about result size limits or what the offset-driven paging returns.

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 no filler, and the retrieval purpose is front-loaded before the responsibility caveat. Efficient, though the middle sentence's emphasis on the assistant's job is slightly instructional rather than descriptive.

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?

An output schema exists, so return values need not be described. But for a tool with an unexplained offset parameter and an unnamed near-duplicate sibling, the definition leaves meaningful gaps about result volume and how this differs from get_continuity_context.

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 all three parameters, so the description carries the full burden. Only 'short proposed scene' hints at proposedText's size constraint; projectId and offset (clearly a pagination cursor) are left entirely unexplained.

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 ('Retrieve locked canon') plus the intended use ('compare against a short proposed scene'), which is far more than a restatement of the name. However, it never distinguishes itself from the close sibling get_continuity_context, so an agent cannot tell the two apart from text alone.

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?

Usage is implied rather than stated: the agent learns it should feed a proposed scene in and then perform the comparison itself. There is no explicit when-not or naming of alternatives (get_continuity_context, search_story_canon), which matters given several canon-reading siblings.

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