search_codebase

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

With no annotations provided, the description carries the full burden. It discloses that the tool returns pre-extracted facts ranked by relevance, supports multi-query with semicolons, deduplicates results, and has a max result cap (limit × queries, max 65). It also implies read-only behavior through 'search' and provides cost-saving context, all of which goes beyond the minimal schema.

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 a bit lengthy but well-structured into purpose, multi-query instructions, and an args breakdown. Every sentence adds value—examples, defaults, and batching logic are all useful. It's not overly verbose given the tool's complexity, but could be slightly tighter.

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 tool with 5 parameters, no annotations, and an output schema, the description is remarkably complete. It defines all parameters, gives usage guidance, explains multi-query and limits, and mentions return behavior (facts ranked by relevance). The presence of an output schema means return structure need not be spelled out.

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%, but the description compensates fully with an 'Args' section that explains every parameter: query, category (with enum-like options), min_confidence (with range and default), limit (with behavior for batched queries), and repo_name. It also gives concrete examples, making parameter usage unambiguous.

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 clearly states a specific action: 'Search the codebase knowledge base for facts about what the code does, how it's built, and what it assumes.' It also distinguishes itself as the first step before reading source files, setting it apart from the more specialized sibling tools like get_module_facts and get_recent_changes.

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?

It explicitly instructs 'Use this FIRST before reading source files' and provides strong guidance to 'ALWAYS batch related searches into one call — this is dramatically cheaper.' While it doesn't explicitly name alternatives, the clear directive to use it first and batch searches gives solid usage context.

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