query_database

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

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly states the read-only nature: 'this tool cannot insert, update or remove documents'. It also warns about the potentially large result of getAll on FileJSONDB and redirects to search_files. This goes beyond the schema and covers the most important behavioral traits, though it does not mention response format or other edge cases.

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 sentences with no wasted words. The purpose is front-loaded in the first sentence, the read-only constraint is in the second, and the important getAll caveat is in the third. The structure is logical and scannable.

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 generic fallback query tool with no output schema and no annotations, the description covers the core requirements: what it reads, that it is read-only, when to use it, and one critical caveat about data size. It does not describe response structure or pagination, but those are less critical given the tool's role as a catch-all and the schema's already thorough parameter documentation.

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?

The schema already covers parameter meaning with 100% description coverage, so the baseline is 3. The description adds extra semantic value by highlighting a mode-collection combination hazard: 'getAll' on FileJSONDB returns the entire file database and recommends search_files instead. This is not present in the schema and helps agents reason about the interaction between mode and collection.

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 opens with a specific verb and resource: 'Read a Tdarr database collection directly (POST /api/v2/cruddb)'. It clearly states the tool's scope as a general-purpose reader for anything dedicated tools do not cover, listing examples like global settings and jobs. It also differentiates from the sibling search_files by explicitly preferring that tool for FileJSONDB getAll, making the boundary between tools apparent.

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 states when to use this tool: 'for anything the dedicated tools do not cover'. It also provides a concrete exclusion: 'prefer search_files there' when using getAll on FileJSONDB. This gives an agent actionable routing guidance relative to siblings, satisfying the when/when-not requirement.

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