security_tables

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

The readOnlyHint annotation already tells the agent this is a safe read, so the description carries a lower bar, but it still discloses nothing beyond that: no return shape, no pagination or result-limit behavior, no scoping rules. The only extra signal, 'of one database', is already implied by the single 'database' parameter.

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 sentence fragment with no filler — nothing redundant to trim. It is terse to the point of under-specification, but that is a completeness problem rather than a conciseness one.

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 simple one-parameter read tool the annotation covers safety, but the description leaves the agent unable to route between this, list_tables, and schema_explorer_tables, and provides no output or scoping detail. Against a crowded security/schema sibling set, that is inadequate context.

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?

Only one parameter exists and schema description coverage is 0%, so the description must compensate. 'Of one database' does clarify that the result set is scoped by the database argument, which is modest added value, but it says nothing about accepted identifier format, defaults, or whether the database must exist in the current connection.

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 phrase 'Tables of one database' does convey the resource returned, but it is a bare noun phrase with no verb and no distinguishing detail. It does not differentiate itself from siblings like list_tables or schema_explorer_tables, so an agent cannot tell why it would pick this one over those without opening schemas.

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?

'For the "who can access" picker' gives an implied usage context that links it loosely to the who_can_access/security family. However, it never states when to use this versus list_tables or schema_explorer_tables, and offers no exclusions or preconditions.

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