job_retry

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

Annotations already declare readOnlyHint=false, destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds genuinely new behavior: execution is asynchronous and must be polled via session tools, retry scope is limited to failed objects, and dry_run previews without retrying. It does not mention permissions or what state is overwritten, so it falls short of a 5.

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?

Front-loads the operation type and purpose, then async/polling guidance, then alternatives, then args — a sensible order with no filler sentences. The Args block partially restates names already in the schema, but given 0% schema description coverage that restatement earns its place.

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 mutation tool with no output schema and three undocumented-in-schema params, the description covers what the tool does, how it executes, how to poll it, and how to preview it safely. The only gap is how the agent obtains the session identifier to poll with, which is left implicit.

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 the parameter burden, and it does — all three args are described (job_id, dry_run semantics, and target as a config-sourced Veeam target name). The notes are terse and don't specify ID format, but they fully cover the parameter set.

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?

States a specific verb and resource ('Retry a failed backup job') plus a scope qualifier ('re-runs failed objects only'), which separates it from job_start and job_get. It also names the inverse sibling (job_stop), so an agent can place it correctly among the job_* family without opening a schema.

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 clear operational context: it runs as an async session, must be polled with session_list/session_get, and supports dry_run=True for preview. It also names the alternative relationship (job_stop cancels the in-flight retry), but never states an explicit when-not condition or contrasts it against job_start.

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