explore_codebase

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

Annotations already establish readOnly/non-destructive safety. The description's real contribution is disclosing the return shape (counts, languages, importance, symbols), which matters because there is no output schema, but it omits pagination/truncation behavior tied to max_items/max_tokens.

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 leading sentence states the operation and output, followed by a compact Args block. No filler; every line carries information, though the Args section could be formatted to match schema parameter names more cleanly.

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?

Compensates for the absent output schema by describing return contents, but with 6 parameters, no required fields, and low schema coverage, an agent still lacks guidance on defaults for max_items/max_tokens and on when this tool is the right pick.

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 only 17%, so the description carries extra weight. It adds genuine meaning for path ('relative to project root'), importance_threshold ('0.0 to 1.0'), and task_hint ('orders the files'), but leaves max_items and max_tokens completely unexplained anywhere.

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?

Names a specific verb and scope ('List one directory level') and describes the return shape: subdirectories with counts/languages, files with importance and symbols. This clearly distinguishes it from deeper-search siblings like semantic_search or project_summary, though it never names them explicitly.

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?

No guidance on when to reach for this over relevant_context, project_summary, fast_search, or semantic_search, despite a crowded sibling set. Usage is only implied by the tool name and 'one directory level' phrasing.

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