search_project_context

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context by noting 'Returns bounded evidence with stable IDs and revisions' and reinforcing 'never changes Premiere', going beyond the annotation-provided safety hints.

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 concise sentences. It front-loads the verb and resource, provides a helpful enumeration of content types, and closes with a clear statement about non-mutation and return value characteristics. No unnecessary words or repetition.

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?

With no output schema, the description adequately describes the return behavior as 'bounded evidence with stable IDs and revisions'. It explains the tool's non-destructive nature and searchable content, but it does not mention prerequisites (e.g., needing to capture project context first) or how to use the returned IDs. Overall, it is sufficiently complete for a read-only search tool but leaves some contextual gaps.

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%, giving each of the 5 parameters a clear description. The description adds extra semantic value by enumerating the searchable content types (sources, timeline placements, transcript passages, shots, audio observations, notes), which maps directly to the 'kinds' enum and helps users understand valid filter values.

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 states the tool's verb ('Search') and resource ('durable Premiere project-context index'), then enumerates the content types covered (sources, timeline placements, transcript passages, shots, audio observations, notes). This clearly distinguishes it from sibling tools like search_project_items, which searches project items rather than a contextual index.

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 implies the tool is for querying a specific project-context index, but it does not explicitly state when to use it over alternatives such as search_project_items or manage_project_context. It lacks direct guidance about when not to use it or mention of any prerequisites (e.g., invoking manage_project_context first).

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