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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description goes beyond that by naming specific side effects it will NOT perform (marking calls read, altering Quo routing), which is exactly the kind of mutation-adjacent ambiguity an agent worries about in a telephony settings context. It stops short of noting auth requirements, rate limits, or whether 'recent calls' is bounded.

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?

It is short (two sentences) and front-loaded with the verb, and every clause carries information about returned data. But the enumeration of eight resource types in a single sentence is unstructured and dense, making it hard to scan; a grouped or bulleted form would serve the agent better with the same word count.

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 no output schema, the description does real work by enumerating what comes back (answering lines, mappings, calls, source digits, case links, event times, history). But for a read across multiple data domains it omits whether 'recent calls' is paginated or time-bounded, and gives no hint about result volume — meaningful omissions for an agent planning a call.

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 0%, so the description is the only place that could clarify the two required parameters — and it says nothing about 'company' (a UUID tenant scope) or 'environment' (staging vs production). An agent must infer from the format and enum alone. This is a real gap: picking production vs staging is a consequential decision left entirely unexplained.

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 ('Read') and enumerates the concrete resources returned: answering lines, Quo number, keypad mappings, recent calls, source digits, case links, event times, settings history. Together with the '_read' suffix versus the sibling 'summer_phone_calls_settings_update', an agent can tell it is the inspection counterpart. The purpose is clear, but the resource list is presented as a flat run-on rather than a grouped summary, so it reads more like a data dump than a crisp statement.

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 closing clause 'Does not mark calls read or change Quo routing' implicitly signals that changes belong to the update sibling, which is a useful negative boundary. However, it never names summer_phone_calls_settings_update or summer_pharmacy_calls_settings_read as alternatives, nor does it state when an agent should call this versus those. Usage is inferred rather than stated.

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