finalize_design_spec

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

Discloses that no LLM call is made, builds slides.html, runs lint, and requires overflow_json. Also specifies return fields. No annotations provided, so description carries the burden well.

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?

Front-loaded with core action, then structured into args, returns, and important follow-up. Every sentence adds value with no fluff.

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?

Covers prerequisites, parameters, return fields, and required follow-up. Given output schema exists, the description supplements it well.

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 coverage is 0%, but description clarifies project_id as required and overflow_json as optional JSON array with default ''. Provides meaningful context beyond schema.

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?

Clearly states it finalizes a deck by building slides.html and running lint. Distinguishes from siblings like ingest_design_slide and export_html by specifying the procedure order.

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?

Explicitly says to call once after all slides are ingested via ingest_design_slide and provides a follow-up step to call export_html. Lacks explicit when-not-to-use but positive guidance is strong.

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