read

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

Annotations already cover safety (readOnlyHint=true, openWorldHint=false), but the description adds real behavioral detail the annotations cannot: the row-oriented return format, pointer naming, and the important truncation trait 'stops at the first unmapped byte,' which tells the agent reads can be partial. It stops short of describing error behavior for a fully unmapped address, so not a full 5.

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 tightly packed sentences with no filler. The primary behavior and output format are front-loaded, and the exclusions are compressed into a single trailing clause.

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 4-parameter tool with full schema coverage, annotations, and no output schema, the description supplies exactly what structured data cannot: the return shape and the truncation-at-unmapped-byte behavior. Address syntax and count limits are adequately handled by the schema, so nothing an agent needs 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 coverage is 100%, so the baseline is 3; the description earns above that by making the mutual-exclusivity of `kind` and `type` explicit ('or a user type (type)') and by tying each parameter to its mode. It does not elaborate on address forms or the 256-value cap, which remain schema-only.

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 (read) plus two explicit decoding modes (kind-based typed values vs. user type) and the output shape (`va value` rows, one row per field, pointers named). It also names what the tool is not (hexdump for raw bytes, live_read for a live process), which lets an agent separate it from siblings without opening any schema.

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?

Provides explicit when-not guidance with named alternatives: 'Not for raw bytes (use hexdump) or a live process (live_read).' The two positive modes described in the first sentence imply the when-to-use case, so an agent has both the selection rule and the routing rule.

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