ghl_kb_upload_file

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

Annotations already declare write/idempotent=false/openWorld, so the description's added value is auth and environment requirements: 'Requires a Sub-Account (location) token' and the 'knowledge-bases.write' OAuth scope, plus the concrete endpoint and returned fields. It does not say what happens on duplicate uploads or whether training/indexing is triggered asynchronously, which is the remaining behavioral gap.

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 the action, then the WHEN TO USE routing, then return values and auth metadata — a good order. Minor waste: the 10MB limit is repeated three times (annotation title, first line, second line), which could be collapsed into one statement.

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 single-body mutation tool with no output schema, the description covers inputs, returns, endpoint, and auth prerequisites. It stops short of stating whether the knowledge base must pre-exist or how long indexing takes, which an agent might need before chaining calls.

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%, with the file parameter already documenting the 10MB limit and PDF/DOC/DOCX formats, so the description's format and size notes are duplicated rather than additive. The nested body/knowledgeBaseId/locationId structure is left entirely to the schema, so the baseline 3 is appropriate.

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 ('Uploads a file to knowledge base') plus accepted formats (PDF, DOC, DOCX) and a size ceiling. It is clearly distinguished from sibling upload paths such as ghl_media_upload_file or ghl_location_upload_file_custom_fields, and it names the KB-specific siblings it complements.

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 WHEN TO USE block gives a positive trigger (adding a document source), names the follow-up and cleanup alternatives (getFilesByKnowledgeBasePublic, deleteFile), and explicitly excludes a nearby wrong path ('Do not use this for website pages — use discoverWebsite / trainDiscoveredUrls'). Nothing is left to inference for tool selection.

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