submit_for_approval

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

Annotations already convey readOnlyHint=false, idempotentHint=false, and destructiveHint=false, but the description adds the key behavioral fact that this is a write operation (submission) that mutates an approval field. However, it does not disclose potential side effects like triggering approval workflows, whether submission is reversible, or whether it checks permissions beyond WRITE_ENABLED. Given that annotations signal mutation, the description adds only marginal behavioral context beyond the 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?

A single, dense sentence with the parenthetical clarifying scope (generic, not just change) and the WRITE_ENABLED prerequisite. Every clause earns its place and is front-loaded with the operation and mechanism.

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 needn't explain return values, but it does not mention failure modes, whether the operation can be recalled (recall_approval_request exists), or whether it respects existing approval state. The generic-record claim and WRITE_ENABLED prerequisite are useful, yet the definition lacks enough behavioral context for a mutation tool with no output schema.

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%, so the schema already documents table, sys_id, and approval_field. The description adds context about the approval_field default ('requested') and that the operation is generic, which slightly enriches meaning. But it does not clarify whether the field must exist on all records or what happens if it is missing, so it does not exceed the baseline 3.

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 (submit for approval), a clear resource (any record), and the exact mechanism (setting the approval field to 'requested'). It also explicitly notes this is a generic operation not limited to change requests, which distinguishes it from sibling submit_change_for_approval. This is a clear, differentiating purpose.

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 explains that this is a generic submission covering any record (not just change records), which implies a contrast with the sibling submit_change_for_approval. It also provides a prerequisite (WRITE_ENABLED=true) that gates invocation. However, it does not explicitly name when to prefer this over alternative approval-related tools or mention conditions like record state, so it falls just short of full guidance.

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