Get Operation Performance

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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, so safety is covered. The description adds genuine context beyond that: results are content-free (privacy posture), the local scope, and that cache occupancy reporting is bounded with missing measurements surfaced as unknown rather than zero. It stops short of saying whether this requires a running analysis job or whether timing windows are reset.

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?

Two tight sentences with no filler, and the scope qualifier ('content-free local') is front-loaded. Slight cost for jargon density, which forces the reader to decode 'stage timing' and 'bounded analysis cache occupancy' rather than state them plainly.

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-value shape needn't be explained. Still, for a metrics/introspection tool among dozens of diagnostics siblings, the description leaves key questions open: what an 'operation' or 'stage' is, whether measurements are per-session or cumulative, and when this tool is the right choice. Adequate but with clear 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?

Both parameters (expected_cep_target, expected_project_path) are fully documented in the schema at 100% coverage, so the baseline is 3. The description adds no parameter meaning at all, and notably never clarifies that these guards are optional and mostly inert for a local-only tool, which is the one thing it could have usefully said beyond the schema.

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 verb ('read') and the resource category (local stage timing, payload sizes, cache occupancy) are stated, which identifies this as a telemetry/diagnostics read. However, the terms 'stage timing' and 'bounded analysis cache occupancy' are internal jargon and the description never says whose operations these metrics cover or how they relate to the sibling diagnostics tools like get_bridge_telemetry or inspect_operation_recovery. Purpose is inferable but not crisp.

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?

There is no guidance on when to call this versus the many adjacent diagnostics tools (get_bridge_telemetry, get_last_operations, inspect_workflow_job, inspect_operation_recovery). No preconditions, no exclusions, no alternatives named. The 'local' qualifier implies it does not touch Premiere, but that is left to inference.

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