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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description's real value is in adding new context: a 30-day or owner-deletion expiry, a short-lived one-hour signed-in download link, and the guarantee that no backup body or credential is returned. These details go well beyond the annotations and clarify side effects, which is exactly what an agent needs for a read tool. It omits pagination or rate-limit behavior, which keeps it from a 5.

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 definition leads with its purpose and mode split, then layers on expiry and download behavior. Most sentences do useful work, but 'No backup body or credential is included' is a slightly awkward negative that could be folded into the download sentence.

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?

No output schema exists, so the description takes on the job of characterizing return content, and it does: before/after metadata, backup references, checks, and Activity steps. The main gap is that three of the five parameters (demoStage, inspectTarget, targetConnection) are never mentioned in the description, so the agent relies entirely on the schema to interpret them.

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 every parameter already carries its own description; the baseline is 3. The description reinforces the listing mode ('up to 100 records') and the download semantics, but it does not explain demoStage, inspectTarget, or targetConnection at all, so it adds only marginal meaning beyond the schema.

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 a specific verb and resource: it 'Lists this organization's saved development plans, or reads one change record with its before and after metadata.' It also distinguishes the two modes by referencing the changeSetId behavior, and it separates the tool from run_change by stating that 'reading a record does not apply, verify or undo it.' Siblings are not named explicitly, so it falls just short of a 5.

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?

It gives concrete timing for use: 'Use it before approving a new transition or to review an unknown outcome,' which tells an agent what context calls for this tool. That is a clear positive condition, but it offers no explicit rule for when not to call this tool or which named alternative to use instead.

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