unw_remaining

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

With no annotations and no output schema, the description carries the full disclosure burden, and it does substantial work by enumerating the returned fields (credits remaining, pick-N progress, status, priority class) and by warning that 'shared_title_with' flags double-counting risk. That caveat is exactly the kind of non-obvious behavioral context structured fields cannot convey. It does not address permissions, caching, or whether the list is filtered by any active plan context.

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 sentences, front-loaded with the scope constraint, then a dense field list, then the authoritative-status claim. Every clause names a distinct returned attribute or a distinct risk; nothing is redundant or padded.

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 zero-argument read tool with no output schema, describing the return contents is the main completeness obligation, and the description does that thoroughly, including the shared_title_with caveat. The remaining gap is scope context — whether results are global or tied to a term/plan — which an agent would need to interpret the list correctly.

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 takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The description instead spends its words on return semantics, which is the only meaningful surface for a parameterless tool.

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 opens with a precise scope statement, 'Unmet requirements only', plus an explicit inventory of the resource's fields, so an agent knows it returns outstanding requirement records rather than courses, candidates, or audits. It never states an explicit verb (list vs. compute), and it does not name a sibling it differs from, so sibling differentiation rests on the phrase 'authoritative what is left list' rather than a direct contrast.

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?

'This is the authoritative "what is left" list' signals when to prefer this tool over related ones, which is genuine, if implicit, routing guidance. There is no explicit when-not-use clause and no alternative tool is named, so an agent must infer that e.g. audit or candidate tools serve different questions.

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