context_open

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

With no annotations provided, the description carries the behavioral burden and does well by disclosing that tenant/company/user scope comes from authentication, that the returned pack is bounded by token_budget, and that it augments but does not enlarge the native context window. This gives an agent useful expectations about side effects and boundaries. It could still note things like error behavior or whether creating context persists externally, but current coverage is strong.

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 well-organized: a front-loaded opening that states purpose and usage, followed by a compact, single-purpose Args list. Every sentence adds information—no filler or repetition of schema titles. Despite describing nine parameters, it remains tight and scannable.

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?

For a complex tool with nine parameters, no annotations, and no schema descriptions, the description provides comprehensive guidance: when to call, how to chain refs, auth scoping, token limits, parameter semantics, and cross-parameter constraints. An output schema exists, so return values are covered elsewhere; nothing critical for correct invocation is missing.

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 0%, and the description compensates fully by explaining all nine parameters, including the pairing constraint between company_ref and project_ref, the token_budget range, the meaning of an empty space_ref, and the ranking role of query. This is exactly the kind of semantic enrichment the schema lacks.

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: 'Open or resume durable private working context for this host session.' This is a specific verb plus resource, and it is readily distinguishable from sibling tools like context_read or context_status. However, it does not explicitly name or differentiate from those siblings, so it falls short of the top score.

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 gives explicit invocation timing: 'Call at task/session start and after compaction.' It also explains how to use returned references on later calls, which is practical usage guidance. It does not mention exclusions or specific alternatives, so it stops short of a 5.

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