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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond that by declaring the returned fields (slug, title, company) in the absence of a proper output schema, and by confirming zero-argument invocation.

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?

Three terse sentences: identity and scope first, follow-up routing second, invocation contract last. No filler, no restating of the tool name, nothing to trim.

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 correctly compensates by listing the returned fields, and it covers invocation with no arguments. The only remaining gaps are ordering and whether the full saved set is returned (pagination/size), which are minor for a personal saved-jobs list.

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?

The tool has zero parameters, so the baseline is 4. 'Takes no arguments' is consistent with the empty schema and preempts an agent from inventing filter arguments, which is the only meaningful parameter note possible here.

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 ('List the jobs the caller saved') and disambiguates from the two other list tools by scoping to saved jobs rather than applications or matches. It also names the three returned fields, so an agent knows exactly what projection to expect 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?

Explicitly routes the agent to get_job for reading a single saved job, which is a clear next-step alternative. It does not state exclusions against list_applications or list_matches, so an agent comparing list tools gets context but not explicit when-not guidance.

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