call_read

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

Annotations declare readOnlyHint/idempotent/destructive=false, but the description adds substantial context beyond them: it avoids an approval prompt, the gate is per-ACTION not per-tool, and a refusal names the actions it would accept. These are genuine operational behaviors an agent could not infer from the annotations or schema.

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?

Front-loaded with the key distinction ('Like call, but restricted to tools that only READ state'), and every sentence carries a distinct piece of information (prompt avoidance, per-action gate, refusal behavior). It runs slightly long and the per-action nuance takes a few clauses to land, but nothing is wasted.

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 gateway/dispatch tool with no output schema, the description covers purpose, when to prefer it, the subtle per-action eligibility rule, and error/refusal behavior. An agent has everything needed to invoke it correctly and interpret a rejection.

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%, so the baseline is 3, but the description adds value by demonstrating the tool/args relationship with concrete examples (args={} and args={'action':'get'}). It does not clarify the optional 'session' parameter, which the schema already documents, so it stops short of a 5.

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 capability (invoke read-only tools) and explicitly contrasts itself with the sibling 'call', which can reach anything. The agent can distinguish the two without opening either schema, and the 'restricted to tools that only READ state' clause pins down the exact scope.

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?

Gives explicit when-to-use (hidden read-only tools), when-not-to-use ('Refuses anything that writes; use call for those'), and names the alternative 'call'. The per-action guidance ('get' works, 'set' does not) tells the agent exactly which invocations are eligible, not just which tools.

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