work_memory_read

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

With no annotations, the description carries the full burden and does disclose non-obvious behavior: a short receipt is returned by default when the same version was already fully returned in this context, reread=true forces a fresh round, and truncated originals are never restored. It stops short of permission/auth or size-limit context, but the deduplication and truncation semantics are genuinely useful disclosures.

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?

Front-loaded with the core read/pagination purpose, then semicolon-separated clauses each carrying distinct behavioral information. It is dense but every clause earns its place; the '文件未完整核验时返回正文' clause is slightly cryptic but not wasted.

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 7-parameter tool with no annotations and no output schema, the description covers behavior well but leaves parameter semantics incomplete (memory_id, max_chars, context_handle) and does not describe what a 'brief receipt' actually looks like. Adequate but with clear gaps.

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 and it only partly does: it explains 'section', 'expected_revision', 'reread', and pagination via offset. It says nothing about 'memory_id', 'max_chars', or 'context_handle', leaving three of seven parameters undocumented anywhere.

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+resource ('按需分页读取工作观察' – read work observations with on-demand pagination), which is clearly distinct from the sibling work_memory_search. However, it never names the search sibling or explains the read-vs-search boundary, so differentiation is implied rather than stated.

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?

Gives concrete continuation-page rules (carry forward 'section' and 'expected_revision', no need to repeat reread) and explains that reread=true starts a new round. That is real when/how guidance, but there are no explicit exclusions or pointers to alternatives such as work_memory_search for locating a memory_id.

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