Create Editorial Context Pack

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

The description adds meaningful behavior beyond the annotations: it explicitly states that the tool never calls an AI/provider or Premiere and cannot change the project, which goes beyond the generic readOnlyHint and destructiveHint flags. It also discloses the return behavior—stable evidence IDs and context revisions for review—giving the agent a clearer model of what invoking the tool will produce. No contradiction with annotations exists.

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 is two sentences long with no filler. The first sentence front-loads the core purpose and inputs, and the second sentence adds safety and output behavior, all in a compact and scannable structure. Every clause earns its place.

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?

Given the rich annotation set, a full output schema, and 100% schema parameter coverage, the description covers the essential non-schema aspects: what the output is for, that it operates on local captured context, and that it has no external or mutating side effects. The tool's complexity is well addressed without requiring the description to duplicate structured metadata.

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 100%, so the schema already documents all six parameters, including the kinds enum, intent, project_id, max_entries, sequence_id, and max_characters. The description adds no parameter-specific detail beyond mentioning the local context kinds, which merely mirrors the enum values. Baseline 3 is appropriate because the schema carries the parameter-semantics burden.

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 description clearly identifies the action (create), the resource (compact Markdown reading view), and the input domain (already captured local transcript, shot, audio, note, source, or timeline context). It also distinguishes itself by explicitly stating that it returns stable evidence IDs and context revisions rather than modifying a project, which separates it from related create/plan tools. This is a specific, non-tautological purpose statement.

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?

The description gives clear contextual guidance: the tool operates on already captured local context and produces a review-oriented Markdown view, so an agent can infer when to call it. It also states what the tool never does (calls an AI/provider or Premiere and cannot change the project), which helps rule out inappropriate uses even though it does not name alternatives explicitly. It lacks an explicit 'use X instead' statement, but the context is sufficiently clear.

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