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

Annotations only establish the safety profile (not read-only, non-destructive, not idempotent, closed-world); the description adds the genuinely useful behavior: it returns a job_id immediately, runs asynchronously for roughly 1-6 minutes, and can enter a 'needs_input' state requiring user interaction. That async/state-machine disclosure is exactly what an agent cannot infer from annotations or schema.

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 sentences, front-loaded with what the tool produces, then the alternative, then the async follow-up protocol. No restatement of the title and no filler; every clause carries operational 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, yet the description compensates by explaining the return value (job_id) and the full polling/resolution loop including the needs_input branch. For a long-running generative tool with four well-documented parameters, nothing an agent needs to invoke and follow up correctly is missing.

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 (prompt, layers, design_id, extra_review) are already documented in the schema, setting the baseline at 3. The description reinforces that prompt is a plain-language functional spec but adds no guidance on layers, design_id continuation semantics, or when extra_review is worth the slower run.

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?

States a specific verb and resource ('Designs a complete, routed, manufacturable printed circuit board') and enumerates the concrete sub-steps (part selection, schematic, placement/routing, DRC). The line 'Use this instead of writing KiCad files by hand' plus the sibling names (edit_board, route_board, run_drc) let an agent place this as the top-level end-to-end tool rather than an incremental editor.

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?

Gives clear post-call routing: poll get_job until status is 'done', and on 'needs_input' surface the question and call answer_question. It also names the alternative it replaces (hand-writing KiCad files). It stops short of explicitly saying when to prefer edit_board/route_board for modifying an existing board versus passing design_id here, so it is strong but not a complete when/when-not map.

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