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

Annotations already declare readOnlyHint=false and destructiveHint=false, so safety profile is partly covered. The description adds real value beyond them: it requires the write scope, and it discloses that resumption preserves full history, which affects how an agent should use it for recovery.

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 tight sentences, front-loaded with the primary action before the recovery use case and the scope requirement. No filler or redundant restatement of the title.

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?

Covers purpose, the main secondary use case, attachment capability, and authentication requirement for a 6-parameter mutation tool with no output schema. Nothing essential to a correct invocation is missing, and return values need not be described.

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 all six parameters (id, text, model, autoRun, budgetUsd, mediaKeys) are already documented in situ. The description only echoes 'optionally with files attached' (mediaKeys) and adds no format or usage detail beyond the 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?

Specific verb+resource: 'Send another message to a job', with 'another' signalling continuation of an existing job rather than creation. It stands apart from jobs_create and jobs_run implicitly, but no sibling is named explicitly, so an agent must infer the boundary.

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?

Gives a concrete when-to-use case beyond the obvious reply flow: resuming a stuck or failed run while keeping full history. No exclusions or named alternatives (e.g. jobs_run vs jobs_continue) are offered, so the routing guidance is clear but not exhaustive.

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