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

Annotations declare destructiveHint=true and idempotentHint=true; the description adds genuinely useful context beyond that: the update is a partial merge ('Only what you pass changes') and widgets are preserved ('its widgets stay'), plus filter scope ('every widget counts only those rows'). It doesn't discuss that a filter change alters what data all widgets surface, but it materially clarifies effect scope.

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?

Two dense sentences, front-loaded with the mutable field list, then the crucial partial-update/scope semantics. No filler; every clause earns its place.

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?

With an output schema and annotations already present, the description supplies the field semantics, filter behavior, and preservation guarantee an agent needs to call it correctly. Minor gap is not mentioning the required dashboardId or name length bound, but these are low-risk.

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 only 20%, so the description needs to compensate, and it does for the optional fields: it names each updatable field and explains the filter's 'sheet.read filter form' semantics and null-clearing. dashboardId (the required param) and the name maxLength of 80 are not addressed in the description.

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?

Specific verb 'Change' applied to the dashboard resource, and it enumerates exactly which fields are mutable (name, icon, description, filter). It's clear what the tool does, though it doesn't explicitly contrast itself with dashboard.create/delete/restore siblings.

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?

'Only what you pass changes' signals partial-update usage and 'null clears it' indicates how to remove the filter, which is implied guidance. However, there is no explicit when-to-use vs alternatives (e.g. dashboard.create, dashboard.restore) or prerequisite guidance.

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