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

Goes well past the readOnly/idempotent annotations: discloses that no triage lease is needed, that unknown profile keys pass through unchanged, that an inbox override's non-standard keys are replaced by a short marker unless full:true, and that `effective` is a deep merge of defaults and override. These are non-obvious behaviors an agent could not infer from the schema.

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 purpose is front-loaded, but the body is one long compound sentence with nested parentheticals (the 2000-character guidance aside is especially hard to parse). Every clause carries information, yet the density makes it slower to scan than it needs to be.

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?

There is no output schema, and the description compensates by enumerating return keys and explaining the marker/pass-through behavior and the `effective` merge. An agent has enough to call it correctly and to interpret what comes back.

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 coverage is 100%, so the baseline is 3, but the description adds real semantics: `full` controls verbatim pass-through versus token-saving markers, and `inboxId` yields a merged `effective` object rather than just the override. This explains the effect of each flag, not merely its type.

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?

States a specific verb and resource ('Returns the account-level triageProfile') and enumerates the contents: cadence, junk rules, VIPs, quiet hours, agentRules, notes, setupCompleted. It is clearly the read counterpart to the mutating sibling update_triage_profile, which the 'Call this before any mutating pass' line reinforces.

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?

Gives an explicit trigger ('Call this before any mutating pass (archive/label/junk/draft batches)') and a conditional usage for inboxId ('Pass inboxId to also get effective ... which is what an agent should actually follow'). It does not name update_triage_profile as the write alternative, but the read-vs-mutate split is clear from context.

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