read_context

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: the tool returns a 'static view' (implying read-only, non-destructive), uses 'sensible default exclusions' when rules=[], and provides guidance on default behavior and targeting efficiency. However, it doesn't explicitly mention permission requirements, rate limits, or error handling, leaving some behavioral aspects uncovered.

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 appropriately front-loaded with core functionality, but it contains some redundancy (e.g., repeating that targets and rules accept JSON arrays) and includes implementation details like 'You can ignore the other arguments by default' that could be streamlined. The 'Guidance for AI Model Usage' section is helpful but adds length. Overall, it's informative but could be more concise.

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 (7 parameters, 57% schema coverage, no annotations, but with an output schema), the description is mostly complete. It covers the core purpose, usage guidelines, parameter semantics for key inputs, and behavioral context. The output schema exists, so return values needn't be explained. However, it lacks details on less critical parameters like 'debug_explain' and 'size_limit_mb', and doesn't mention error cases or performance implications.

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 57%, so the description must compensate. It adds significant value beyond the schema: it explains that 'targets' and 'rules' accept JSON arrays, clarifies that empty rules ([]) use sensible defaults, provides examples of default exclusions, and gives practical guidance on when to use specific targets versus processing the entire root. However, it doesn't fully explain all 7 parameters, particularly 'debug_explain' and 'size_limit_mb'.

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 purpose: 'Reads context from a specified project root directory' and 'Returns a static view of files with paths relative to the project root.' It specifies the verb (read), resource (context/files), and scope (project root directory), distinguishing it from the sibling 'usage' tool which provides documentation rather than file reading.

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 guidance on when to use this tool: 'Assume the user wants to read in context for the whole project unless otherwise specified' and 'If the user just says 'jinni', interpret that as read_context.' It also specifies when to use the list_only argument: 'If the user asks to list context, use the list_only argument.' This gives clear usage rules and context for invocation.

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