Graph Ingest

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

Annotations provide idempotentHint=true, and the description adds that queueing the same file twice overwrites the prior copy. It also explains the asynchronous nature and nightly dream process. More detail on destructive behavior or auth needs would be nice, but the description adds value beyond annotations.

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?

The description is three tight sentences with no filler. Each sentence presents a distinct, valuable point: setting modes, usage guidance, and idempotency. Front-loaded with action description.

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?

Given 3 parameters, no output schema, and sibling tools, the description covers purpose, usage, and behavioral traits well. However, it does not describe what the 'status' mode returns (output format missing), leaving a small gap in completeness.

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?

Input schema has 100% parameter coverage, so baseline is 3. The description adds no additional meaning beyond what the schema provides (e.g., file_path required for queue is already in schema description). Satisfactory but not exceeding 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?

The description clearly states the tool does two things: queue a document for async extraction or check the ingest backlog. It uses specific verbs and resource ('queue a document', 'check the ingest backlog') and distinguishes from sibling tool graph_relate by specifying when to use each.

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 explicitly says when to use this tool ('when you have a file the user wants summarized into the graph but doesn't need it reflected in the same conversation') and when not to (for inline assertions, use graph_relate instead). It provides clear context and alternatives.

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