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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful behavioral context beyond them: images may be unavailable, merged captures are included, and legacy tests are supported. It stops short of explaining pagination behavior implied by limit/offset.

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 core action, but the four sentences are loosely stitched, with caveats ('Images may be unavailable', 'Legacy tests also supported') appended rather than organized. Reasonable size, uneven structure.

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-format explanation is unnecessary. For a 6-param read tool the description covers retrieval source, defaulting, availability caveats, and legacy support – adequate, with limit/offset behavior the only notable omission.

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 only 33%, so the description must compensate. It does map frameNumber to its source (finding evidence) and blockId/runId to list_test_blocks IDs with default behavior, but limit and offset are left entirely undocumented in both schema and description.

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 ('read one gallery frame') and identifies the key input (frameNumber from finding evidence) plus the return content (one available image preview, merged captures). It is clear what the tool does, though it never explicitly contrasts with near-neighbors like get_screen_details or get_insight.

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?

Gives one concrete routing hint – 'Use IDs from list_test_blocks to target a block/run' – and notes omission falls back to documented defaults. However there is no guidance on when to prefer this over get_screen_details/get_insight, nor prerequisites or exclusions.

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