tracking.inspect

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds 'Risk: read; maturity: L3' and 'Per-request argument checks and session policy still apply', which gives some operational context beyond the annotations. However, it does not describe actual behavior such as what is inspected, whether output is truncated, or how errors surface, so the added value is modest.

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 short and compartmentalized into risk, maturity, and requirements, which is efficient. However, the first sentence merely restates the command name and provides no functional content, so one of the few sentences does not earn its place. It is concise but under-informative rather than sharply front-loaded.

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?

The presence of an output schema helps explain return values, and annotations cover safety, but the description still fails to state the tool's core purpose or when to use it. An agent has enough metadata to know the call is safe and idempotent, but not enough to understand what inspection means or how to invoke it correctly. This is inadequate for a tool with a single required functional parameter.

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?

The description says nothing about the required `clip` parameter, which is the central input and is not described in the schema either. Schema coverage is 60% and the internal parameters are individually documented, but the key functional parameter receives no semantic explanation from the description. The tool name makes the clip connection inferable, but this does not substitute for explicit parameter semantics.

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 says only that this is the `tracking.inspect` command and that it is read-risk, without stating what it does with the `clip` argument or what it returns. It is essentially a restatement of the name/title plus a risk label. An agent cannot tell whether it inspects tracking markers, solve results, or clip metadata.

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 about when to use this tool versus siblings like `blender_tracking_load_clip`, `blender_tracking_add_track`, or `blender_tracking_solve_camera`. The only operational note is that argument checks and session policy apply, which is not usage context. The description implies a read/inspect role but never states the workflow position or alternatives.

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