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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds substantial context beyond them: hard limits (8 tool calls, 8 documents, 24000 chars, 3 files at 16000/24000 bytes), shared trial quotas, no arbitrary code/shell/VM/logins, variable search availability, and the explicit caveat that quotes are matched but factual correctness is not verified. It also discloses where artifacts land (result.agent_result.artifacts) and that required_artifacts enforces delivery by exact filename.

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 lead sentence establishes what the tool is and the limits follow, with no filler sentences; every statement carries operational information. The prose is dense and telegraphic ('Quotes are matched; tool outputs and factual correctness are not independently verified') and version-specific clauses are interleaved, which makes it harder to scan than an ideally structured definition.

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?

With no output schema, the description does the necessary work of saying outputs appear in result.agent_result.artifacts and that get_studio_job must be polled for status. It covers prerequisites, quotas, and safety boundaries. Remaining gaps are the undocumented consent/idempotency_key/access_token semantics, which are largely conventional.

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%, so the description must carry parameter meaning, and it partially does: version enum values are mapped to concrete capabilities, documents count/size limits are spelled out, and required_artifacts is explained as exact filenames to require delivery. However, consent, idempotency_key, and access_token are never mentioned, leaving three of four parameters to be inferred from the raw 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 states a specific resource and action: a local worker agent that reads supplied documents and produces artifacts, submitted as a job. It distinguishes capability tiers (v1 document reading, v2 CPU/RAM functions and file formats, v3 web read/search), so an agent knows what class of work this handles. It never contrasts itself with siblings like submit_chat_job or submit_compute_job, so differentiation is only implicit through 'local worker agent'.

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 gives conditional usage guidance: set version=2 for decimal/file work, version=3 requires services.agent_web, and check services.agent_tools for v2 availability. It also tells the agent to poll get_studio_job after submitting. There is no explicit when-not or 'use X sibling instead' routing, which keeps it out of the top band.

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