get_context

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It openly states that it returns 'selective/compact context,' implying it may not contain all details, and lists exactly what it returns (goal, state, decisions, bugs, TODOs, files changed, next action). It also explains the fallback path. While it doesn't discuss side effects or permissions, for a read operation this is sufficient and adds meaningful behavioral context.

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 slightly verbose but every sentence carries value: purpose, timing, content, and fallback. It is front-loaded with the primary purpose and immediate usage instruction. The phrase 'most important tool for cross-session continuity' adds emphasis but could be trimmed without losing information. Overall it is well-structured and not overly long for the complexity.

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 there is no output schema, the description compensates by enumerating the exact fields returned and explicitly noting the selective nature. It covers when to use, what it returns, and what to do if data is missing. It doesn't specify response format or error conditions, but for a read tool with clear fallback guidance, the description is sufficiently complete for correct invocation.

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 100%, so the schema already documents all four parameters with descriptions. The tool description adds minimal parameter-specific information—it mentions auto-detection of project via workspace_path indirectly, but that's already in the schema. Since the schema handles parameter semantics fully, the description doesn't need to compensate, so a baseline 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 clearly states the verb ('Retrieve'), the resource ('continuation context from previous sessions'), and the scope ('for the current project'). It also distinguishes itself from sibling tools by naming the exact context to retrieve (goal, state, decisions, bugs, TODOs, files changed, next action) and by positioning itself as the primary cross-session continuity tool, making it easy to differentiate from search_memory, search_history, and get_session.

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?

Provides explicit timing instructions: 'Call this IMMEDIATELY after start_session and BEFORE making significant changes.' It also gives clear fallback guidance: if specific info isn't found, use search_memory() for durable facts or search_history() for detailed events. This tells an agent exactly when to use this tool and when to switch to alternatives, leaving nothing to inference.

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