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

readOnlyHint=true already declares this as a safe read, so the description is not carrying the full burden. The 'Bloomerang: GET /interactions' mapping adds modest confirmation of the read-only, endpoint-backed nature, but says nothing about result caps, default ordering behavior, or cost.

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?

A single dash-separated sentence: purpose first, filter capability second, endpoint reference last. No filler, and the most important information is front-loaded.

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?

Annotations cover safety and the schema covers all eight parameters, but because there is no output schema the description could reasonably say what a result looks like (paginated interaction records, default ordering by Date). As written, an agent must infer the return shape entirely from the parameter set.

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 100% with eight fully documented parameters, so the schema does the heavy lifting and baseline 3 applies. The description's mention of constituent, channel and purpose filtering mirrors the schema without adding syntax, defaults, or interaction between filters.

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 clear verb (List) and resource (interactions), and enumerates concrete interaction types (calls, emails, meetings, letters) so the agent knows what domain this covers. However it does not differentiate itself from siblings like bloomerang_get_constituent_timeline, which likely also surfaces interaction data.

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 phrase 'filter by constituent, channel or purpose' implies the search-oriented use case and maps to real parameters, giving implicit guidance. There is no explicit when-to-use vs alternatives statement, nor any exclusion such as when a timeline or single-interaction fetch is preferable.

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