typed_memory

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=false, so the safety profile is carried by structured data. The description adds the typing constraint ('struct-aware', width_bits values) but says nothing about write semantics, alignment requirements, or the optional session parameter's effect, so it adds only modest behavioral context beyond 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?

Two short, front-loaded sentences with no filler: purpose first, then the allowed signatures and value constraint. The pipe/equals notation is compact though slightly terse for reading, keeping it just below maximally clear.

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 6-parameter, dual-mode tool with no output schema, the description covers the required-parameter model but omits return values, error behavior on misaligned/out-of-range addresses, and how 'typed' semantics differ from the raw memory tools. Annotations cover the safety side, so this is adequate but visibly incomplete.

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 100%, so the baseline is 3. The description restates the read/write parameter signatures and the width_bits enumeration, both of which are already expressible from the oneOf branches and the enum, so it adds little meaning beyond the schema.

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 gives specific verbs and resource ('Typed (struct-aware) memory access') plus the concrete signatures for read and write, so an agent knows exactly what operations it performs. However, it never distinguishes itself from the sibling tools read_memory and write_memory; the only differentiation is the vague parenthetical 'struct-aware', which the agent must interpret on its own.

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, no statement of preconditions (a live debug session is implied by the sibling set but not stated), and no comparison to the raw read_memory/write_memory alternatives. Usage is only inferable from the action syntax, which the schema already provides.

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