inspect_motion_frames

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes beyond them by specifying the data provenance: 'checksum-verified completed motion' and 'missing metadata remains explicitly unavailable'. That tells the agent results are trustworthy and that absent fields are meaningful gaps rather than errors. It does not mention prerequisites on job state (must be completed) as an explicit precondition.

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?

Four short sentences, output payload stated first, constraints second, provenance third, edge-case behavior last. No filler; even the negations ('not rendered pixels or invented poses') carry disambiguating information.

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 values need not be described, and provenance/caveats are covered. However, with zero schema description coverage the description should have addressed sample_index and job_id semantics, and it should have flagged that the job must be in a completed state for checksum-verified data to exist.

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 0%, so the description must carry the load. It clarifies frame_indices (up to 16, ordered), joint_names (optional, named subset), and include_rotations (optional rotation matrices), but job_id and sample_index — including its 0-3 bounds — are entirely unexplained, leaving two of five parameters undocumented anywhere.

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 a specific verb+resource ('Read selected source frames') and enumerates the returned data (joint positions, hierarchy, timing, rotation matrices). It implicitly differentiates from preview_motion by stating it does not return rendered pixels, though it never names the sibling it competes with (inspect_motion, which appears to operate at a coarser granularity).

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?

Usage is described only in parameter terms ('select up to 16 ordered frames and optionally named joints'), with no guidance on when an agent should reach for this instead of inspect_motion, preview_motion, or extract_motion_constraints. The 'not rendered pixels or invented poses' clause hints at a boundary but never states a selection rule.

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