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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces 'Read-only'. Beyond that it discloses the actual response shape an agent otherwise could not know without an output schema: the four status values, ruleSettled entries tagged 'structured' vs 'rules', per-file conflict kinds, editability, saved drafts, and that exact git commands are included. It does not discuss network/auth requirements beyond the schema-level cache note.

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 content is dense and largely earns its place, but it is delivered as one sprawling sentence with nested parentheticals, making it hard to scan. The purpose is front-loaded, yet the enumeration of conflict kinds and hunk fields could be structured far more cleanly.

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 5-parameter read tool with no output schema, the description does the heavy lifting on return contents and ties the output to the follow-up resolution tool. Only minor gaps remain, such as what an 'unknown' merge status means operationally and how the shared probe cache interacts with repeated calls (left to the `fresh` schema text).

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 baseline is 3, but the description adds real meaning for `hunks: true` — that each editable file gets diff3 text labelled by branch name with hunks shaped as (id, mine, base, main) intended for gluecron_resolve_pr_conflict. That is semantics the schema does not convey. `fresh` is left to its schema description, so it is not a full 5.

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 states specifically that this reports what blocks a PR from merging: merge status, mergeable flag, base/head shas, settled vs. unresolved files, and drafts. It is more evocative than a clean verb+resource phrase ('What stands between a PR and a clean merge...'), but it clearly names the resource (a PR's conflicts) and points at gluecron_resolve_pr_conflict as the consumer of its hunks output, which separates it from generic siblings like gluecron_get_pr.

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 implied: this is the inspection step before calling gluecron_resolve_pr_conflict, and hunks:true is called out as the mode for that path. However, there is no explicit when-to-use vs. when-to-use-something-else (e.g., gluecron_pr_status_summary, gluecron_get_pr, gluecron_get_pr_checks) and no stated exclusions or prerequisites.

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