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

Annotations already declare readOnly=true, idempotent=true, and destructive=false, so the safety profile is covered. The description adds valuable behavior beyond that: it is 'a static reference,' it 'returns no live counts,' it 'costs nothing,' and it 'reads no workspace data.' These contextual constraints are genuinely useful for an agent deciding whether to invoke it in a given situation. No contradiction with annotations.

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?

At roughly 110 words, every sentence earns its place: purpose, call conditions, topic semantics, and behavioral caveats. The topic enumeration is compact but runs together in one dense block, and a bulleted list would improve scannability. Minor structural nit against otherwise tight prose.

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?

An output schema exists, so return-format details need not be spelled out. The sole parameter is fully documented in both schema and description, annotations cover the operational profile, and the description covers purpose, usage triggers, topic content, cost, and data-access behavior. For a tool whose job is to resolve the complexity of hundreds of siblings, nothing needed to call it correctly is missing.

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% but the schema's param description ('Which map to return. Defaults to overview.') is thin. The description goes substantially beyond it by explaining what each enum value actually contains in practical terms: watchers ('how to choose between the seven ways to monitor something'), workflows ('which tool creates which kind'), platforms ('what can be acted on and what is tracking-only'), and outreach_and_safety ('who sends, what the limits are'). This converts bare enum names into actionable selection guidance.

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 opens with a specific verb-resource pair: 'Explain how the pieces of this workspace fit together, so you can pick the right tool.' This clearly positions the tool as an orientation/reference utility and distinguishes it from the hundreds of operational sibling tools, which it names as the objects of its guidance. It also enumerates five concrete topic areas, leaving no ambiguity about what it covers.

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?

The description gives three explicit call conditions: 'choosing between similar tools,' 'a request does not obviously map to one tool,' and 'an error tells you to consult it.' It also routes away from itself by stating it 'returns no live counts' and pointing to the specific list tools (campaignstack_list_signal_agents, campaignstack_list_workflows) that should be used instead. This is explicit when/when-not guidance with named alternatives.

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