ContextBuilder (ctx)

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 mentions 'graph-based retrieval and observation masking', which hints at technical implementation but doesn't clarify behavioral traits like whether this is a read-only operation, potential side effects, performance characteristics, or error handling. For a tool with 9 parameters and no annotations, this leaves significant gaps in understanding how it behaves.

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, efficient sentence that front-loads the core purpose. Every word earns its place: 'Pull' (action), 'targeted context slice' (resource), 'for an app' (scope), 'based on intent, budget, and required sections' (key parameters), and 'Uses graph-based retrieval and observation masking' (implementation hint). No wasted words.

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 (9 parameters, nested objects, no output schema, and no annotations), the description is inadequate. It doesn't explain what a 'context slice' actually contains, how the graph-based retrieval works, what 'observation masking' means, or what the output looks like. For a sophisticated retrieval tool with multiple constraints and no structured output documentation, users need more context to use it effectively.

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 high (89%), so the baseline is 3. The description adds minimal value beyond the schema by mentioning 'intent, budget, and required sections' in the purpose statement, but doesn't provide additional context about parameter interactions, typical values, or usage examples. It doesn't compensate for the 11% gap in schema coverage.

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 action ('Pull a targeted context slice') and resource ('for an app'), specifying it's based on intent, budget, and required sections. It distinguishes from siblings by mentioning graph-based retrieval and observation masking, which none of the sibling tools reference. However, it doesn't explicitly differentiate from all siblings (e.g., vs 'ctx.get.app_state_summary').

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 no guidance on when to use this tool versus alternatives like 'ctx.get.app_state_summary' or 'ctx.get.provenance'. It mentions the parameters (intent, budget, sections) but doesn't explain the appropriate contexts or scenarios for choosing this tool over others. No exclusions or prerequisites are stated.

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