analyze_reference

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

With no annotations, the description carries the full burden. It does disclose a non-obvious behavioural trait: the response contains a framework plus the image, and the agent must fill in the analysis itself. It says nothing about whether the call mutates state, permission requirements, or what happens with an unknown referenceId.

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 short sentences with no filler, and the return-shape disclosure is front-loaded. The phrase "with the image for visual inspection" is slightly awkward but carries real 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?

There is no output schema, so the description is the only place the return value could be explained — yet the structure of the "framework prompts" is never described (what sections, what format the agent should fill in). For a tool whose entire purpose is handing back a fill-in template, that is a meaningful gap.

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 description coverage is 100%, so all four parameters (including the lookup accelerators seriesId and sketchId and the previewSize default) are already documented in the schema. The description adds nothing beyond "reference image", so the baseline of 3 applies.

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 uses a specific verb+resource ("Return a structured analysis framework for a reference image") and clarifies the unusual division of labour: the tool does not analyze, the agent does. That distinguishes it from update_reference_analysis and critique_sketch, though neither sibling is named explicitly.

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 only implied — an agent infers it should call this before analysing a reference image. There is no explicit when-to-use, no exclusion of alternatives such as critique_sketch or update_reference_analysis, and no mention that the result is presumably written back via update_reference_analysis.

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