tandem_context_read

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

With no annotations, the description bears the full burden of behavioral disclosure. It provides some negative constraints ('does not select another context, read files, or grant execution rights') which is useful, but it fails to state whether the operation is read-only, how pagination works, or what side effects exist. The mention of 'capsule pointers' is not explained in behavior terms.

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 four sentences but the opening sentence is cryptic and not front-loaded with the core purpose. It is not concise in meaning; it wastes words on vague phrases like 'Page omitted product data' and 'pinned snapshot' without adding clarity. The structure does not help an agent quickly grasp the tool's function.

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 4 parameters (1 required), an output schema, and 20 siblings, this description is critically incomplete. It does not explain the pagination concepts (offset_bytes, max_bytes), what 'capsule pointers' are, what data is returned, or how this tool fits into the broader workflow. An agent cannot reliably invoke it correctly based on this description alone.

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%, so the description must compensate for the lack of parameter explanations. It mentions 'capsule pointers' (likely referring to the 'pointer' parameter) but does not explain 'task_id', 'max_bytes', or 'offset_bytes'. The default and boundary values exist in the schema but their purpose is not explained in the description.

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 states 'Page omitted product data from this task's immutable pinned snapshot,' which is vague and does not clearly identify the action (e.g., 'read' or 'retrieve') or the resource being accessed. The phrase 'capsule pointers' adds confusion rather than clarity. It does not effectively distinguish from siblings like 'tandem_work' or 'tandem_review'.

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?

There is no explicit when-to-use guidance. The line 'Follow capsule pointers rather than repeatedly loading the whole product' implies an alternative but does not name a sibling tool. 'Independent review uses its pinned review reader instead' hints at an alternative but again without identification, leaving the agent to guess when this tool is appropriate.

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