get_work_context

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the 'bounded' trait, indicating results are limited, but does not specify how bounds work (e.g., default limits, configurable via the limits parameter) or mention the 'include' parameter's role in selecting sections. This adds minimal behavioral context beyond annotations.

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?

One sentence with no filler: 'Get bounded task, blocker, decision, checkpoint, and recovery context.' It is front-loaded with the verb and resource, and every word carries meaning. This is 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?

The tool is a read operation with a rich schema (5 parameters, nested limits object, include enum) and an output schema. The description provides the high-level purpose, and the schema already documents details like default behavior and parameter constraints. Given the annotation coverage and schema richness, the description is sufficiently complete for an agent to select the tool correctly, even though it does not mention integration points like project_ref or agent_session_handle.

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% coverage with descriptions for all parameters (e.g., issue_id: 'Issue whose work context to load', include: 'Optional unique context sections; empty returns the compact default'). The description's list of context types (task, blocker, decision, checkpoint, recovery) loosely maps to schema enum values but does not add further parameter-level detail. Since the schema handles parameter semantics comprehensively, a baseline score 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 uses a specific verb 'Get' and a resource 'work context' with a 'bounded' qualifier, enumerating the context types (task, blocker, decision, checkpoint, recovery). This clearly indicates the tool's purpose and distinguishes it from siblings like 'get_issue' by focusing on a bounded aggregate view, though it does not explicitly mention aggregation or a composite nature.

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. It does not mention exclusions, prerequisites, or alternative tools, and there is no contextual hint about appropriate use cases. The list of context types implicitly suggests a holistic view, but this is not explicit enough to count as usage guidance.

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