maintenance

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

Beyond the annotations, the description discloses meaningful behavioral traits: the operation is 'bounded deterministic', executes no commands or model calls, 'All changes preserve history', and uncertain semantic conflicts remain queued. This strongly shapes an agent's expectations and adds real value over 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?

Three sentences, each carrying distinct information: the available modes, the non-execution and no-guessing constraints, and the history-preservation guarantee. The most decision-relevant guidance is front-loaded with no filler.

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 multi-mode tool with a nested evidence object and no output schema, the description gives a strong safety profile but not a complete operational picture. It never states what the durable queue contains, what actions like dismiss/supersede/consolidate/accept-candidate do, or what a successful invocation returns. It is adequate but has clear gaps.

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 only 29%, and only id and winner_id have inline descriptions. The description does not explain the seven parameters, the enum meanings, or the nested evidence object's required fields. It contributes the idea of 'checked evidence', but that is insufficient compensation for largely undocumented parameters.

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 names the tool's three modes — run, queue, and resolve — and specifies what each acts on: 'maintenance', 'durable queue', and 'ONE job using checked evidence'. This is more specific than a tautology and gives an agent a clear sense of the operation. It does not, however, distinguish itself explicitly from sibling tools like record, amend, or consolidate.

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 provides clear behavioral context: it is safe because 'No commands or model calls are run', uncertain conflicts should be left queued for host-agent review, and replacements should never be guessed. What it lacks is an explicit when-to-use-this-vs-alternatives statement against the listed siblings.

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