gograph_explore

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

Beyond the annotations (readOnlyHint/idempotent/destructive:false, which already establish the safety profile), the description adds genuine behavioral context: source analysis is refreshed before the call, possible dispatch is excluded from bundled identity impact and deep traversals, compact/deep are mutually exclusive, and question-like text is lexical rather than model-interpreted. 'Read-only; no persistent side effects' is redundant with the annotations, but the other disclosures are valuable and non-contradictory.

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 definition is dense but front-loads the core purpose before diving into modes, constraints, and return shape, so an agent can extract the essentials quickly. Some sentences are load-bearing (mutual exclusivity, dispatch exclusion, refresh behavior), though 'Read-only; no persistent side effects' duplicates the annotations and the overall length is on the heavy side.

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 multi-mode aggregation tool with no output schema, the description supplies the missing return-value information explicitly via the RETURNS block (shared gograph.explore.v1 with mode, selection_basis, ambiguity, totals, truncation, omission metadata) and covers mode defaults, limits, and exclusions. Nothing an agent needs to invoke this correctly appears to be missing.

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 all five parameters including the compact/deep exclusivity and the clamped 1-100 limit. The description reinforces mode defaults (5/25) but adds little semantic detail beyond what the schema provides, matching the baseline for full schema coverage.

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 opening sentence gives a specific verb and resource (explore a lexical term or Go symbol) and frames the tool as a single bounded aggregation call that bundles matches, source, callers/callees, tests, and impact. It differentiates itself from the many focused siblings by noting that 'focused tools remain authoritative for complete output,' which tells an agent this is the bundled-overview option. The differentiation is meaningful though it references the sibling class generically rather than naming specific tools.

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 description clearly explains the mode-selection conditions (compact for low-token discovery, deep for expanded evidence, mutual exclusivity, explicit limit overriding defaults) and when to prefer this over focused tools for complete output. It provides strong usage context but stops short of explicit when-not-to-use guidance or naming the specific alternative tools for a given task.

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