get_contents

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

Goes far beyond the readOnlyHint annotation by disclosing two independent bounds (20 refs and 40,000 chars), the deferred return field and budget_chars, the never-cut behavior, the special case of a single row exceeding the budget, and the ownership check via agent_id that results in missing. This level of behavioral detail is exceptional.

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 description is dense and every sentence provides meaningful detail about limits, edge cases, and the deferred mechanism. It is longer than average, but the complexity of the tool justifies the length; the version reference '2.5.4a2' adds specificity without being redundant.

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?

Given the multi-bound behavior, deferred refs, budget semantics, and the absence of an output schema, the description covers all critical runtime behavior, edge cases, and the ownership check result. The agent receives everything needed to invoke the tool correctly and interpret results.

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% and both refs and agent_id are already well-described in the schema. The description adds contextual behavior (deferred, missing) but does not add new parameter-level semantics, so the baseline of 3 is appropriate.

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 opens with 'Fetch full, untrimmed content for recall preview refs', which clearly specifies the action, resource, and scope. It also distinguishes this tool from the preview-tier recall flow by positioning it as the targeted expansion path, differentiating it from sibling tools like recall and recall_with_context.

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?

Explicitly states when to use the tool ('Use after a preview-tier recall to expand only the rows that matter') and names the alternative approach ('instead of opting the whole recall out with full_content=true'). Also gives operational guidance about re-fetching deferred refs in a second call.

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