describe_cell

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

No annotations are present, so the description carries the full behavioral burden. It does disclose the returned content and the depth expansion behavior, which is useful, but says nothing about permissions, whether it mutates session state, cost limits, or error conditions for an unannotated tool.

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?

Purpose is front-loaded in a single sentence, followed by a compact Args block that maps one-to-one to parameters. No filler or redundant restatement.

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 detailed (though it summarizes them anyway), and all parameters are explained. The remaining gap is the absence of usage routing against siblings, which is minor given the low-complexity, read-oriented nature of the tool.

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 0%, so the description must compensate, and it does: it documents all three parameters, including the meaning of depth (levels to expand, 0 = none) and the origin of session_id (returned by open_layout). This adds real meaning beyond the bare schema titles.

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 states a specific verb and resource ('Describe one cell') and enumerates the outputs (bounding box, child instances, text labels, shapes per layer). This distinguishes it from sibling list_cells, though it never explicitly names that sibling to route the agent.

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?

It implies a prerequisite by noting session_id comes from open_layout, giving a basic workflow hint. However, it offers no explicit when-to-use/when-not guidance versus list_cells, query_region, or measure_geometry, leaving selection largely to inference.

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