Call Read Tool

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open world), and the description adds real context beyond them: execution goes through the target's own validation and guards, is audited, preserves the target's result format, and keeps secret scrubbing active. The notable extra is the warning about state-changing routes hidden behind GET in the mixed relay — a genuine runtime caveat not derivable from annotations. It does not say what the caller sees when the named tool is missing or disabled, 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 opening sentence front-loads the purpose and the second carries the most important constraint, so scanning works well. The Args section repeats the input schema almost verbatim, which is mild redundancy rather than harm. No filler sentences.

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?

For a dispatcher tool with a free-form nested arguments object and no output schema, the description covers the essentials: what it dispatches to, the read-only guarantee, scrubbing, and the write refusal. Remaining gaps are error behavior and whether 'enabled' implies a discovery step via list_tool_families or search_tools. Those matter for a dispatcher but do not block a correct 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 100%, so the schema already documents both fields and the description's Args block largely duplicates it, including the same examples. The only added meaning is the word 'enabled' on name, hinting that a tool must be enabled to be callable, and the clarification that arguments follow the target's schema. That is marginal value over the structured data, so the 3 baseline applies.

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 states a concrete verb and resource — execute a read tool — and immediately scopes it by listing what the call preserves (validation, guards, audit, result format). It also separates itself from the sibling call_write_tool by declaring that write calls are refused, so an agent can pick correctly without opening either schema.

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 exclusion is explicit: write calls, including state-changing routes of the mixed GET relay, are refused, which effectively routes write intent to call_write_tool. 'Describe the target first; its schema and permissions apply' gives a required prerequisite step. It stops short of naming the write alternative or the safe fallback when a tool name is disabled, so it is strong but not exhaustive.

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