run_discovery

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds behavioral context: the tool filters noisy inputs, returns only evidence, handles broad scopes, and accepts 'safe commands.' It does not contradict the annotations and provides useful extra context beyond them.

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 well-organized and front-loaded: purpose first, usage guidance second, and a compact bulleted parameter list. Every sentence contributes useful information, and the example for terminal_commands is valuable without adding unnecessary length.

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?

The description covers purpose, usage, and key parameters, but the tool has no output schema and the description gives only a vague sense of the return value ('return only the evidence'). It also does not explain how budgets, snippets, or command allowlist profiles affect behavior, so an agent may not know how to tune or interpret the 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 0%, so the description must compensate. It explains the core parameters well: objective, objective_type, scope_paths, query_hints, and terminal_commands, including a concrete example. However, it omits several meaningful parameters such as raw_read_budget, max_files, return_snippets, and command_allowlist_profile, leaving gaps an agent must infer.

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 starts with a specific action verb and resource ('Explore noisy docs, logs, or codebases') and clearly states the output ('return only the evidence a parent agent needs'). It also enumerates the supported objective types, making the tool's purpose unmistakable.

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 explicitly states when to use the tool ('discovery or triage before reading raw files itself'), lists best cases, and gives a concrete exclusion ('Do not use it for final file edits or precise patch generation'). This gives an agent clear routing guidance even without sibling tools.

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