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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real substance the annotations cannot: the HUMAN_EDIT_AFTER_AGENT_SYNC conflict guard, that force is audit-logged, and that it overwrites the human's newer edit. It stops short of describing the failure response shape or what a rejected patch returns, but the mutation-risk profile is well disclosed.

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, each serving a distinct purpose: what fields, which sibling handles status, and the conflict/force rule. The most decision-critical constraint (conflict guard) is placed last but the routing guidance is front-loaded, and no sentence is filler.

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 13-parameter destructive mutation with no output schema, the description covers field scope, identifier form, sibling routing, and conflict/override behavior. The remaining gap is return-value and partial-failure behavior, plus semantics of nulling fields beyond dueDate, but the critical call-time decisions are all supported.

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 only 23%, so the description must compensate, and it does for the fields that matter most: it flags labels and acceptanceCriteria as set-replace semantics, which is nowhere in the schema, and states the ticket-key-or-UUID identifier convention. Type/priority enums are left to the schema and per-field formats (dates, points bounds) are uncovered, keeping it below 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?

Opens with a specific verb+resource ('Patch fields on an existing story') and enumerates the exact patchable fields, then explicitly names the sibling it is not (stride.update_story_status). An agent can distinguish it from create_story, bulk_update_stories, and assign_story without opening any schema.

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?

Explicitly routes status transitions to stride.update_story_status and notes that tool carries the optional comment. It also states the precondition for force:true (human's explicit approval) and the default rejection behavior, so both the normal and override paths are covered.

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