context_read

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

With no annotations at all, the description carries the full disclosure burden. 'Read' usefully implies a non-destructive operation, and 'opaque refs' correctly signals these are pass-through handles that should not be parsed or interpreted. However, it does not disclose failure modes (invalid/expired refs), whether token_budget truncates output, or any permission/scoping constraints.

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?

A single sentence with zero filler. The verb and resource are front-loaded, and every remaining phrase ('exact', 'opaque refs', 'returned from pack or search') adds discriminative value rather than restating the name.

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?

The output schema covers return values, but the description omits too much else: 5 parameters at 0% schema coverage, no annotation safety profile, and no guidance on refs_json serialization format or token_budget truncation. For a tool sitting in a family with context_pack/context_search/context_open, an agent gets enough to call it but not enough to call it correctly on the first try.

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 meaning of all 5 parameters. It only clarifies that refs (presumably refs_json) are opaque handles, leaving the format of refs_json (JSON array? object?), the role of space_ref, the scoping semantics of company_ref/project_ref, and token_budget behavior entirely undocumented in both schema and 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 names a specific verb ('Read'), a specific resource ('context items'), and the input mechanism ('opaque refs'), which is exactly the distinguishing feature: this tool consumes refs rather than producing them. The provenance clause 'returned from pack or search' explicitly ties it to sibling tools context_pack and context_search, so an agent can differentiate it immediately.

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 context: use this when you already hold refs produced by pack or search. However, it never explicitly states when NOT to use it (e.g., 'use context_search when you lack refs' or 'use context_open for a different surface'), so the guidance is inferred rather than stated.

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