phabricator_document_search

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

The readOnlyHint annotation already declares this is a safe read operation, so the safety profile is covered. Beyond that the description adds nothing: no disclosure that it returns paginated results (despite after/before cursors), no note that 'attachments' must be opted into to get content, and no mention of full-text matching semantics. For a 7-parameter search tool this is a thin behavioral picture.

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?

The single phrase is front-loaded and wastes no words, but this is under-specification rather than concision — a 7-parameter search tool with nested constraint objects warrants at least one more sentence about what can be filtered and how results come back.

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?

With nested constraint and attachment objects, pagination cursors, and no output schema, the description should explain that results are paginated, that content/projects/subscribers are only returned if requested via attachments, and roughly what the constraint fields cover. None of that is present, leaving the agent to reverse-engineer usage from the schema alone.

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 100%, so every parameter including the nested constraints and attachments objects is documented in the schema itself. The description adds no additional meaning (e.g., which constraint fields are combined with AND vs OR, or that parentPaths is direct-children-only versus ancestorPaths at any depth). Baseline 3 applies when the schema carries the full load.

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 ('Search') and a specific resource ('Phriction wiki documents'), which distinguishes it from the sibling mutation tools document_create, document_edit, and document_add_comment. It doesn't explicitly name a sibling or clarify how it differs from other search tools like phabricator_file_search, but the resource is unambiguous.

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 gives no guidance on when to use this search versus other search tools (task_search, file_search, paste_search, repository_code_search) or when to use document_edit instead. No prerequisites, no note about query construction, and no mention of what happens with zero constraints.

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