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

With no annotations, the description carries the full burden and does a lot: it discloses permission level ("org admin"), scoping semantics ("scoped to calls EMITTED UNDER this org, never to membership"), ordering ("newest first"), archival behavior ("`content_archived` = its body went to cold archive, only its bounds remain"), and the silent-failure trap for agents. It stops short of stating read-only safety or result-size/pagination limits, which is a real but modest gap for a 17-param tool.

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 scope/audience statement and the op enumeration are front-loaded, and almost every clause is op-specific information that could not be dropped given twelve ops. The ⚠️ agent-failure passage runs long and the slash-delimited op list packs several ideas per line, making it harder to scan than it needs to be, but there is little true 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 twelve-op, seventeen-parameter tool with no output schema and no annotations, the description supplies enough to choose an op and predict its shape (agg dimensions for summary, timeline for run, grouped-by-reason for agents_en_echec). The unexplained `_org` and `limit` parameters and the absence of any note on volume or pagination are the remaining holes.

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%, so the description must compensate, and it does for nearly every parameter: it assigns `days`, `sub`, `tool`, `errors`, `run_id`, `session_id`, `min_duration_ms`, `error_contains`, `call_id`, `signal`, and `status` to the specific op they filter, and gives the format hint "`since`/`until` ISO". Two parameters, `_org` and `limit`, are never mentioned, which keeps it below a 5.

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?

Names the resource and audience precisely ("Observability of YOUR org (org admin)") and then enumerates all twelve ops with what each one returns, e.g. "adoption (member by member: who actually uses oto, who never did, who is blocked by a connector)". It also explicitly contrasts itself with the sibling oto_admin_monitoring ("Platform-wide investigation is oto_admin_monitoring (platform admin)"), so an agent can route without opening either 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?

States the required scope ("`org_id` required"), the when-to-use for the tool as a whole versus the platform-admin sibling, and even intra-tool selection rules such as gaps/tool_quality being AGGREGATED counts versus signals being "the same reports RAW, with their body — the counts say how many, only the body says why". The agents_en_echec warning tells the agent exactly which situation calls for that op.

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