Discover .ia-eval.yaml LLM test suite files in the project directory. Scans CWD and standard sub-directories (evals/, tests/, contracts/). Returns file paths ready to pass to run_eval_contract.
| Name | Required | Description | Default |
|---|---|---|---|
| dir | No | Directory to scan (defaults to server CWD) |
| Name | Required | Description | Default |
|---|---|---|---|
| dir | No | ||
| count | No | ||
| files | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish that the tool is read-only, idempotent, and non-destructive. The description adds behavioral context by specifying the scan locations (CWD, evals/, tests/, contracts/) and the output format (file paths ready for run_eval_contract). However, it does not detail edge-case behavior such as error handling, recursion depth, or how the optional 'dir' parameter interacts with the default scan paths, leaving some behavioral aspects undisclosed.
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 two sentences that are succinct and front-loaded. The first sentence states the primary purpose, and the second explains the output's usability. No unnecessary words or redundant content are present, making it highly concise and well-structured.
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 tool's low complexity (one optional parameter), the annotations covering its safety, and the presence of an output schema, the description provides sufficient context. It informs the user of typical scan locations and that the results are directly consumable by run_eval_contract. It slightly lacks context about the behavior when 'dir' is provided versus the default CWD scan, but overall it is complete enough for its scope.
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?
The input schema has 100% description coverage for the only parameter 'dir' with a clear description ('Directory to scan (defaults to server CWD)'). The tool description does not add extra parameter details beyond this, so it does not enhance what the schema already conveys. With high schema coverage, a 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 clearly states the tool's function: 'Discover .ia-eval.yaml LLM test suite files in the project directory.' It specifies a concrete verb ('Discover'), a well-defined resource ('.ia-eval.yaml LLM test suite files'), and scopes the action to the CWD and standard subdirectories. It also distinguishes itself from the sibling run_eval_contract by noting that it returns file paths ready for that tool, making the purpose unambiguous.
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 implies the usage context: you use this tool to locate local test suite files that can subsequently be passed to run_eval_contract. This provides clear context for when to use it, though it does not explicitly mention alternatives or exclusions. The connection to run_eval_contract gives a practical use case without explicitly saying 'use this before running tests.'
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Multiple tools overlap significantly: compare_models/llm_fit_finder/model_info/list_llm_models all compare models; similarity_score/embedding_similarity/run_semantic_tests all measure text similarity; detect_secrets/secret_scan/analyze_diff_bugs/pr_gatekeeper all scan for secrets. Descriptions attempt to differentiate, but the boundaries between many tools are unclear, making selection error-prone.
The vast majority of tools follow a snake_case verb_noun pattern (validate_email, generate_uuid, parse_csv), making the set mostly predictable. A few notable deviations exist (pr_gatekeeper, llm_fit_finder, cot_analyzer, jira_to_test_suite, needle_haystack_generate) but they are the exception rather than the rule.
With 149 tools, this set is far beyond the 50+ threshold for an extreme mismatch. Even as a general-purpose QA & Dev toolkit, the sheer number overwhelms and exceeds any reasonable scope, making discovery and selection impractical.
The toolkit covers an impressively broad range: text processing, LLM evaluation, security auditing, web checks, MCP validation, Jira/Confluence integration, and more. Minor gaps exist, such as missing delete/update for webhooks and Confluence pages, and no create/update for Jira issues, but these are workable around.