Read Merge Conflict File Version

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=true, so the safety profile is covered. The description adds meaningful behavioral context: backend download behavior (whole file downloaded before client-side slice), byte-length targeting with potential +3 UTF-8 bytes, nextOffset continuation semantics, and chunked return format. It also clarifies the read-only nature for manual resolution, going beyond the 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?

The description is dense but organized: core purpose first, then behavioral constraints, then return format details, then parameter semantics. Every sentence adds information; there is no filler. It is longer than the typical tool description, but the complexity of chunked reads, encoding variants, and side selection justifies the length. The front-loading of the read-only/manual-resolution constraint is effective.

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 tool with no output schema, the description covers the return envelope (MIME, byte-range, nextOffset, hasMore), the side semantics, the file-path provenance, and the encoding forms. It doesn't explicitly document the exact JSON envelope field names beyond nextOffset, but the output is client-side and an agent can infer the structure. Given the 7 parameters and chunked-read complexity, the description is nearly complete, with only minor room for more explicit output-field 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?

Schema coverage is 100%, so the schema itself documents all 7 parameters thoroughly. The description adds value by explaining the byte-length semantics (up to 3 extra UTF-8 bytes), the continuation pattern via nextOffset, and the default encoding behavior. The description's mention of 'JSON text envelope with MIME and byte-range metadata' complements the response_format parameter. The file path provenance from openl_get_merge_conflicts also reinforces the file parameter's meaning.

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 clearly states the tool reads one BASE, OURS, or THEIRS version of a conflicted file as read-only evidence for manual resolution. It explicitly says it never infers or applies a winning side automatically, distinguishing it from merge-resolution tools. The exact file path source is named (openl_get_merge_conflicts), making its purpose 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 explicitly instructs to use the exact file path from openl_get_merge_conflicts and frames this as evidence for manual user resolution, implying it should not be used to auto-apply changes. While it doesn't name specific alternative tools for applying resolutions, the behavioral constraint 'Never infer or apply a winning side automatically' provides clear when-not-to-use guidance. The explicit file-path sourcing also removes ambiguity about which conflict to read.

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