add_net_label

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it delivers: the 'millimetres regardless of document Units' gotcha is a genuinely non-obvious behavior that would cause subtle bugs; the dry_run preview semantics with the expected_sha256 confirmation flow is a rich side-effect disclosure. This goes well beyond what a minimal read of the schema would reveal, though it could note whether the operation participates in the transaction system visible among siblings (begin_transaction/commit_transaction).

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?

Three tightly-written sentences with zero fluff. Sentence one states what + the units gotcha; sentence two states the dry_run contract; sentence three states the confirmation workflow. Every word earns its place and the structure follows a logical safety-first order.

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 10-parameter mutation tool with 0% schema coverage and no annotations, the description captures the essential operational recipe: units, preview mode, and confirmation handshake. The 'net-bound' vs text nuances and multi-sheet implications (sheet param) could use a sentence, but with an output schema present, return-value explanation isn't needed. The coverage is appropriately proportional to the tool's complexity.

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. It does clarify the most critical params — units for x/y, the dry_run/default-true safety behavior, and expected_sha256 as the confirmation token. However, the relationship between `net`, `text`, and `path` remains ambiguous: is `text` the displayed label while `net` is the target net? What is `txid` used for? The description covers maybe 4 of 10 parameters functionally, which is a partial but incomplete compensation.

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+scope: 'Add a net-bound text label shape to a schematic sheet.' The qualifier 'net-bound' differentiates it from plain text annotation tools, and 'to a schematic sheet' scopes the operation. This clearly distinguishes it from siblings like set_text_visibility or add_wire.

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?

The description gives clear operational context ('dry_run=true previews... Set dry_run=false only after inspecting the preview') but never explicitly addresses when to use this tool vs alternatives. No named siblings or exclusion criteria are provided. The workflow is clear but the tool-selection guidance is only implied, not stated. Compared to the HIGH calibration example that explicitly says 'use search_calls_extensive instead,' this lacks an explicit alternative reference.

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