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

Goes well beyond the annotations: it discloses the pre-read of current state, optimistic concurrency via stale expectedUpdateTime rejection, the invariant that the original UTC calendar day is never changed, vendor-side company-date rules, the published-shift restriction, and the absence of automatic write retries. These are operational traits an agent cannot infer from readOnlyHint=false / destructiveHint=true / idempotentHint=false, and they directly shape safe retry and error-handling behavior.

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?

Front-loaded with the action and the confirm gate, and every clause carries real information (no filler). The semicolon-chained telegraphic style packs several distinct constraints into one sentence, which is efficient but slightly reduces scanability.

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 high-complexity mutation with 10 parameters and no output schema, the description covers safety and invariants well but leaves the agent guessing on partial-update semantics (omitted vs null fields) and on the meaning of several parameters. It also gives no notion of what a successful response or a rejected stale-update response looks like.

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 20%, and the description compensates for only part of the gap: it explains confirm=true and the role of expectedUpdateTime as a staleness guard. It says nothing about start/end format, the meaning of released, or whether an omitted field is left unchanged versus cleared — significant omissions for a 10-parameter mutation tool.

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 ('Update one shift') and narrows scope to a single shift after user review, which distinguishes it from the sibling create/list/get tools. The 'confirm:true required' clause immediately signals this is a gated mutation rather than a read.

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 a clear activation condition ('after user review; confirm:true required') and several when-not constraints ('Published shifts cannot be unpublished', 'No deletes', 'inspect uncertain outcomes'). It does not explicitly name a sibling alternative, but the sibling set contains no other update tool, so the routing ambiguity is low.

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