discover_entries

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

With no annotations, the description carries the full burden, and it does disclose a meaningful trait: the return is raw candidates and scores as JSON, not source code, which prevents misuse. However it says nothing about permissions, whether the operation is read-only, rate limits, or the shape/size of the result beyond 'raw'. Partial disclosure only.

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?

Two short sentences, zero waste, with the most important constraint (JSON diagnostics, not code) front-loaded ahead of the alternative-tool pointer. Nothing needs trimming or reordering.

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 7-parameter tool with no annotations and no output schema, the definition is too thin: the output is described only as 'raw candidates and scores as JSON' with no structure, and none of the tuning parameters are explained. An agent would know when to call it but not how to call it or what it will get back.

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 schema has 0% description coverage across 7 parameters (task, maxFiles, maxLeads, maxJevFiles, maxCandidates, maxRelevantFiles, maxRelevantDirectories), so the description must compensate and does not. No parameter is named or explained; the meaning of the various caps and their interaction is left entirely to inference from names and defaults.

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 states a specific verb (returns) and resource (raw discovery candidates and their scores as JSON), and explicitly frames the tool as diagnostics rather than source retrieval. It clearly distinguishes itself from retrieve_dependency_context, though it never spells out what domain the 'discovery' covers. An agent can tell it apart from its siblings, which is the key bar.

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 names the alternative ('For finding the code a task needs, use retrieve_dependency_context instead') and the condition that selects it, plus the 'Diagnostics' label implies the intended context. It stops short of an explicit positive 'use this when...' statement, but the exclusions are clear enough to route an agent correctly.

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