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

Goes well beyond annotations: discloses that stale/busy documents reject the write (concurrency/optimistic-locking behavior), that untouched sections and legacy fields remain, and that plain text/metrics default to AI provenance while rich text carries its own aiGenerated marks. This is meaningful context the structured fields don't convey.

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-loads the purpose before workflow and constraint details, and each sentence carries operational information. It is dense and long but almost nothing is filler.

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 no explanation; the description covers the prerequisites, write semantics, provenance rules, concurrency failure mode, and recovery guidance. An agent has everything needed to invoke it correctly.

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?

Despite 0% schema description coverage, the description explains the important parameters: documents (version-1 rich nodes copied from the read), section_text (plain text, one format per section), text_origin semantics, expected_updated_at (must match exactly, including null), and idempotency_key. project_id/validation_project_id and the market_sizing structure get less explicit treatment.

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 (save) and resource (validation research workspace edits), scoping it to the seven-section document and TAM/SAM/SOM estimates. This clearly distinguishes it from siblings like validation.regenerate_section and validation.export_document.

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?

Names the prerequisite sibling (read validation.get_project first) and tells the agent to pass expected_updated_at exactly, plus how to pick text_origin. It gives strong context but doesn't explicitly contrast with alternatives such as regenerate_section or open_workspace.

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