phabricator_owners_search

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

readOnlyHint=true already declares this is a safe read, so the description only needs to add operational context — and it adds little. Notably it never mentions that owned paths are only returned when attachments.paths is set, nor does it describe pagination behavior despite after/before/limit params. No contradiction with annotations.

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 compact sentences with the core identification front-loaded; nothing is wasted. The second sentence slightly restates the first ("list ownership packages" vs "Search Owners packages"), which keeps it from a 5.

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 7 parameters, nested constraint/attachment objects, no output schema, and only a readOnlyHint annotation, the description should explain the search-vs-list modes and the attachments requirement. It covers the search case adequately but leaves the agent guessing about return shape and how to actually get owned paths.

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%, including nested constraints (paths, name, owners, phids) and the queryKey enum-like values, so the schema carries the parameter burden and baseline 3 applies. The description only loosely maps to constraints.paths ("code path") and adds no syntax, format, or combination guidance beyond that.

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 gives a specific verb and resource ("Search Owners packages") plus a plain-language gloss ("code ownership") and two concrete use cases: find who owns a path, or list packages. That is enough to distinguish it from nearby siblings like repository_code_search or project_search. It stops short of explicitly naming when a sibling such as repository_search would be the better pick.

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 only implied: "Find who owns a code path or list ownership packages" suggests a path-lookup mode versus a listing mode, but no when-to-use/when-not-to-use guidance or alternatives are named. With ~60 sibling tools including repository_code_search and project_search, an agent gets no explicit routing help.

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