Update one capsule section—State, Decisions, Next—or append a Session log entry while preserving other sections, so agents keep shared workspace context current.
Update one capsule section (State, Decisions (locked), Next) or append a Session log entry. Other sections are preserved.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | ||
| text | Yes | ||
| agent | Yes | ||
| token | No | ||
| section | Yes |
Changes observed during successful MCP inspections.
v0.5.11Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden. It does disclose one real behavioral trait — 'Other sections are preserved' — clarifying partial-update semantics, but it says nothing about authentication requirements for the 'agent'/'token' parameters, whether the 'Decisions (locked)' section can in fact be rewritten, what happens on a missing section or slug, or whether changes are reversible.
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?
Two short sentences, front-loaded with the action and its scope, then the preservation guarantee. Nothing is padded and every clause adds information.
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 five-parameter mutation tool with no annotations, no output schema, and zero schema descriptions, the definition is too thin: identity/auth parameters, slug semantics, and the outcome of a call are all left unspecified.
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% across five parameters. The description only clarifies the 'section' enum values and implies 'text' is the content written, while 'agent', 'token', and 'slug' receive no explanation at all — a significant gap for a tool that mutates shared state.
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?
States a specific verb and resource ('Update one capsule section') and enumerates the four valid targets (State, Decisions (locked), Next, Session log), so an agent can distinguish it from workspace_get_capsule. It stops short of naming the read sibling explicitly, but the write-versus-read split is obvious.
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 implies the usage pattern — touch exactly one section per call, or append to Session log — which is useful scoping guidance. It gives no explicit when-to-use versus workspace_get_capsule or workspace_put_context, and no prerequisites or ordering advice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.