get_deviations

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

With no annotations, the description carries the full disclosure burden; it does establish that results are date-ordered ('dated list') and enumerates the content categories covered. However, it never resolves the scope puzzle created by the schema — it references 'an indicator's account' while the tool accepts zero parameters, leaving unclear whether results are account-scoped or global. No mention of auth requirements, limits, or whether the list is complete versus a recent window.

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?

A single front-loaded sentence with no filler; the content enumeration leads and nothing is repeated. It is perhaps slightly over-broad ('other deviations') where a tighter scope statement would have earned more, but the length is appropriate.

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?

An output schema exists, so return values need no explanation, and a zero-parameter read tool is simple enough that a short description can suffice. The remaining gap is scope: nothing states whose deviations these are or whether the list is bounded in time, which matters because there are no parameters to narrow the result.

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 no parameters, so there is nothing for the description to disambiguate and the baseline applies. The absence of parameters does, however, make the phrase 'an indicator's account' slightly confusing rather than clarifying.

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 a concrete resource — bugs, outages, stops and other 'deviations' — and says it is a dated list tied to an indicator's account, so an agent knows what comes back. It stops short of distinguishing this from siblings like get_latest_issue or get_delayed_issue, which cover overlapping incident-style content, so an agent cannot route between them on the description alone.

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 guidance on when to call this instead of get_latest_issue, get_delayed_issue, or list_issues, all of which plausibly return related incident data. No exclusions, prerequisites, or selection criteria are given.

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