get_schema

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

The readOnlyHint=true annotation already declares the safety profile, and the description is fully consistent with... annotation contradiction absent. The description adds value by disclosing what the tool RETURNS (property table, nested drill keys) and documenting the data-flow prerequisite (input derived from get_endpoint output). For a read-only tool whose annotation covers the risk profile, this is solid supplementary detail. No contradiction between '获取' and readOnlyHint=true.

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 sentences with zero filler. The first defines purpose and output; the second resolves the input sourcing. No repetition of what annotations or schema already provide — it's tight, information-dense, and every word earns its place. This is the model of conciseness.

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 tool (1 param, no enums, no nested objects) with an output schema handling return-type doc and annotations covering the read-only profile, the description is nearly complete. It establishes the retrieval flow and content. The main gap is minor: it doesn't address the arrow-prefix format ambiguity or explicitly suggest downstream actions (e.g., passing a schema to select/get_batch).

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?

Although schema description coverage is 0%, the description compensates by explaining the single parameter's provenance — 'schema 名从 get_endpoint 输出的 `→ get_schema(Name)` 中获得'. For a one-argument tool, this effectively documents what 'name' is and where to find it. The only shortfall: it doesn't clarify whether the '→' arrow is part of the literal string value.

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 states a specific verb+resource — '获取单个 schema 的属性表与嵌套下钻键' (get a single schema's property table and nested drill-down keys) — going beyond a tautology by specifying what is retrieved. The '单个 schema' scope distinguishes it from list-like siblings without naming them. It would earn a 5 with explicit sibling differentiation, but the core purpose is unambiguous 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?

The description explicitly tells the agent where to get the `name` parameter: 'schema 名从 get_endpoint 输出的 `→ get_schema(Name)` 中获得' — establishing a call sequence and naming a sibling tool (get_endpoint). This is concrete, actionable guidance for the critical input-sourcing question. However, it doesn't mention when NOT to use this tool or contrast with select/get_batch, leaving a small but real gap.

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