ik_project_analyze

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

With no annotations provided, the description carries the full burden of disclosure. It reveals significant behavioral traits: it is parser-based (not fuzzy), returns a specific set of structural data, and optionally runs the real compiler for authoritative errors. It also discloses the inheritance semantics of `target` across files. It does not explicitly state it is read-only, but the term 'analyze' strongly implies non-mutating behavior, which is acceptable.

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 single dense paragraph that front-loads the key purpose and enumerates concrete return items. Every sentence adds useful information, but it is long and somewhat run-on; a list or clearer sentence breaks would improve scannability. Still, it avoids redundancy and earns its 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?

Given the tool's complexity (multi-file project analysis) and the absence of an output schema, the description compensates well by explicitly enumerating the return values (import graph, target and declaration location, @main entry, per-file exports, cross-file problems) and the optional diagnostics mode. It also provides procedural context for when to use it. This is a complete and self-contained description.

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 already provides 100% description coverage for all three parameters, so the baseline is 3. The description adds value by clarifying that `path` can be a directory or a single file, and that `files` can be used 'instead of a path', plus explaining the effect of `include_diagnostics` as 'compile the entry point for authoritative errors'. This goes beyond the schema's default descriptions.

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 with a specific verb ('Understand') and resource ('multi-file ik project structurally'), and differentiates itself from alternatives by emphasizing 'exact, parser-based — not fuzzy search'. It enumerates specific outputs (import graph, target, @main, exports, problems), making the purpose distinct from sibling tools like ik_compile or ik_check.

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 provides explicit when-to-use guidance: 'Use this BEFORE editing an existing project so you write in the right context' and gives a concrete example of why ('don't re-declare target in imported files'). While it does not name specific alternative tools, it implies a contrast with fuzzy search and clearly scopes the intended use case, but lacks explicit when-not-to-use or named alternatives.

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