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

With no annotations supplied, the description carries the full burden and does so thoroughly: data returned as recorded, long values shortened with truncated lists { path, kind, originalSize }, a maxChars response budget, and explicit terminal states (executed: false with ranIterations, tooLarge: true, olderRunsHiddenByPlan: true). Permission/visibility behavior is at least flagged rather than hidden.

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?

Purpose is front-loaded and followed by calling modes, then result shape, then edge cases, so the ordering is sensible and nearly every clause carries unique information. The prose is dense and semicolon-chained, making it slower to scan than it needs to be, but there is little true filler.

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 complex 8-parameter read tool with no annotations and no output schema, the description covers return fields (success, error, input, output, retryAttempts and its subfields), the per-mode extra fields (nodeId, iteration, startedAt, durationMs), truncation behavior, and degrade states. An agent has enough to invoke it correctly on the first try.

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 must supply all meaning, and it does for blockExecutionKey, instanceKey, nodeId, iteration (default 0, position inside the innermost loop), match, path (syntax plus concrete examples like output.items.[3].body), and maxChars (range 2000..60000, default 30000). The required workspaceId is never explained, which is the only real gap against 8 parameters.

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 and resource: 'Input, output and error of one execution of a block in a run.' It also distinguishes itself from siblings by naming the two upstream sources of its keys (get_flow_instance for blockExecutionKey, list_flow_instances for instanceKey), so an agent can place it in the tool graph without opening a 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?

Gives explicit calling guidance: two mutually exclusive ways to call, 'Do not mix the two ways,' and a defined follow-up path when nested loops produce multiple matches ('repeat the call with match or a blockExecutionKey'). It does not contrast itself with adjacent diagnostic tools like get_flow_instance_logs, which is the only missing routing guidance.

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