get_frame

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

Annotations already signal read-only, idempotent, and non-destructive behavior. The description adds a non-obvious output convention: coordinates are normalized fractions (0.0–1.0) rather than pixels, and it clarifies the limit semantics. It does not contradict the annotations, so the disclosure is solid.

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 front-loaded with a one-sentence purpose, followed by a necessary coordinate-normalization caveat and a compact Args block. No filler or redundant repetition of schema fields.

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?

For a two-parameter frame fetch with an output schema and strong annotations, the description covers the key semantics: what is returned, the coordinate system, and limit constraints. It does not need to explain return structure because the output schema exists, and no missing usage context undermines its completeness.

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?

With 0% schema description coverage, the description compensates fully: frame_id is explained as a numeric id, and limit is given a range (1-100) and default (20) beyond the schema's plain integer/null type. The only minor issue is that the schema specifies default null while the description says 20, but the added guidance is substantial.

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 opens with 'Fetch one frame with its OCR text boxes and parent segment context,' naming a specific verb (fetch), resource (frame), and payload. This clearly distinguishes it from list/search siblings like list_segments, segments_by_tag, and search_text. It is not a tautology or vague.

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 explicit statement of when to use this tool versus alternatives such as list_segments or search_text. The description implies 'fetch a single frame,' but it does not state prerequisites, fallback cases, or when not to use it. This is the weakest dimension.

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