ContextCapsule

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

The annotations declare readOnlyHint=true and destructiveHint=false, but the description includes mutating actions like create, share, delete, revoke_share, which contradict the read-only hint. This is a serious inconsistency that could mislead the agent. The description itself is detailed but contradicts the 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?

The description is relatively long but front-loaded with the core purpose and usage guidelines. It uses a list of use cases which is easy to scan. Some redundancy exists (e.g., explaining share behavior multiple times), but overall it is well-structured 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 the tool has 33 parameters and 15 actions, the description covers intended usage scenarios and defaults. However, it lacks explanation of return values (no output schema) and does not fully detail all actions. It relies on the schema for parameter details but provides enough context for agent decision-making.

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 coverage is 100%, so baseline is 3. The description does not add significant meaning beyond the per-parameter descriptions in the schema, though it provides some context on defaults (e.g., max_uses, expires_in_days). The description does not repeat parameter details.

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: 'portable, shareable, hydrate-on-demand snapshots of project context.' It lists specific use cases (pasting /c/<token> link, handoff requests, etc.) and explicitly distinguishes from the sibling tool 'context' (normal turn-by-turn retrieval).

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 when-to-use scenarios (e.g., user pastes a capsule token, asks for handoff/share link, wants to bootstrap a fresh agent) and an explicit when-not-to-use (normal retrieval should use context). It also details behavior of different share types (authenticated team links vs token-gated single-use public/external links).

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