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

With readOnly/destructive/openWorld annotations already covering the safety profile, the description still adds meaningful context: redacted inputs only, no credential requirement, and an explicit enumeration of what it does NOT do (no code inspection, no patch generation/application, no inference, no score-equivalence validation). This is a strong exclusions list, though the return shape remains unstated.

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?

Two dense sentences that front-load the core purpose before constraints, with no filler sentences. The exclusion clause is long but each item earns its place by closing off misinterpretation. Slightly jargon-heavy but structurally sound.

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 tool with 8 required parameters and no output schema, the description establishes boundaries and safety well but says little about how the enum values affect the plan or what the 'guidance' returned looks like. An agent can call it without erroring, but cannot predict the result. Adequate, with a clear gap in input/output semantics.

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 0% across 8 required parameters, so the description carries the full burden. It only gestures at input nature ('redacted enums and counts') and explains nothing about python_sdk, native_model, source_shape, request_identity, selected_files, prosody_only_literal, or other_batch_operations beyond their self-describing enum values. This leaves most parameter meaning to inference from the schema alone.

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 states a specific verb and resource: it returns bounded planning guidance for a local Hume batch migration, derived from redacted enums and counts. This clearly distinguishes it from siblings like oruk_transcribe_audio or oruk_analyze_tone. It stops short of 5 because 'bounded planning guidance' is abstract and the caller must infer what the output actually is.

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?

It establishes key usage conditions ('No key is needed') and explicitly routes source-bound work elsewhere by naming 'the separate local planner.' Combined with a clear list of what never to send, an agent knows the context in which this tool applies. It does not, however, contrast usage against any sibling by name.

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