company_exceptions

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

No annotations are provided, so the description carries full responsibility for explaining side effects. It implies an action ('Open exception cases') and returns a summary ('summarise the desk'), but does not disclose whether it modifies state, creates records, or only reads. The lack of any annotation (e.g., readOnlyHint, destructiveHint) makes the behavior unclear.

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?

The description is short and compact, but it sacrifices clarity for brevity. It lacks structured elements like a clear action statement, parameter descriptions, or output specification. The run-on sentence mixes input context and output expected results, making it harder to parse.

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?

The description mentions some output aspects ('summarise the desk: open, past SLA, what each waits on') but omits critical context about input format, how the three JSON parameters relate to the described concepts, and what exactly 'open exception cases' entails. Given the complexity of the domain and the presence of an output schema, the description is incomplete for an agent to confidently invoke the tool.

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%, and the description does not explain any of the six parameters (now, project_id, bundle_json, covers_json, tick_result_json, observations_json). The jargon terms in the description (e.g., 'tick result' vs 'tick_result_json', 'cash covers' vs 'covers_json') are not explicitly mapped to parameter names. An agent cannot infer what values to provide or their formats.

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 uses cryptic domain jargon ('a tick result, observer dispositions, cash covers, chains in reconciliation, overdue obligations') without clearly defining what 'open exception cases' means or what the tool actually accomplishes. It does not clearly state a verb-resource relationship like 'list exception cases' or 'create exception cases'. The purpose is ambiguous and not clearly differentiated from sibling tools like 'company_exception_cases' or 'list_aoc_ticks'.

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?

There is no explicit guidance on when to use this tool versus alternatives. The phrase 'Open exception cases from what was refused' hints at a trigger condition (refused items) but does not explain the expected input or context. No mention of prerequisites, typical scenarios, or how it relates to other tools (e.g., 'company_tick', 'list_aoc_ticks').

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