get_bytes

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

No annotations are provided, so the description carries the burden. It implies a read-only operation and discloses the return shape ('返回 addr,data(hex)'), which is useful. But it says nothing about permission/auth needs, read limits, or behavior on unmapped addresses, leaving real gaps for an unannotated tool.

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?

Three short, front-loaded sentences: purpose first, then input format, then return. Dense and waste-free, though the input-format sentence largely restates the schema.

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 low-complexity two-parameter read tool with no output schema, the description covers purpose, accepted input forms, and the return shape (addr + hex data). The instance_id routing requirement is handled by the schema. Nothing critical 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 description coverage is 100%, so the baseline is 3. The description's format examples for 'addr:size' duplicate what the schema already documents for the regions parameter, adding no meaning beyond the structured field.

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: '从内存读取原始字节' (read raw bytes from memory). This clearly distinguishes it from get_int, get_string, and find_bytes by the raw-byte scope. However, it does not explicitly contrast with those siblings, so a 4 rather than 5.

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?

Usage is only implied by the purpose — read raw memory regions. There is no explicit guidance on when to prefer this over get_int/get_string/disasm, nor any stated prerequisites beyond the schema-embedded instance_id note. Adequate but with a clear gap.

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