scan_database

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds genuine value beyond them: it enumerates what is returned (object type, comment, approximate row count, counts) and, critically, states what is NOT done ('不读取业务行'). It stops short of disclosing cost/limits of the approximate row counting.

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?

A single front-loaded clause leads with the verb and scope, and every element earns its place, including the terminal negation '不读取业务行' which meaningfully bounds behavior. No filler or redundancy.

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 read-only catalog scanner with no output schema, the description adequately establishes scope and return contents, and annotations carry the safety profile. But it says nothing about the filtering parameters (name_pattern, object_types) or the limit/pagination behavior, leaving the 50% schema-coverage gap unaddressed.

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 50%: connection, database, and schema carry rich descriptions, but limit, name_pattern, and object_types have none. The description adds no parameter-level meaning at all, so it does not compensate for the undocumented half. Baseline 3 given the schema already handles the required parameters.

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 concrete verb (扫描/scan) and resource (表/视图目录 - table and view catalog) scoped to an exact database/schema within a DBeaver connection, and explicitly notes it does NOT read business rows. The scope is well drawn, but siblings like search_catalog and get_table_context are not named in the description itself for differentiation.

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 implied rather than stated: the 'returns metadata, does not read business rows' framing signals a catalog-inspection use case as opposed to a data-reading one. However, the description never says when to prefer this over search_catalog, list_schemas, or get_table_context; that routing only appears in the schema-level description of the 'schema' parameter.

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