working_promote

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

The description states it will 'tombstone the source', indicating a destructive action, but the annotation destructiveHint is false. This is a direct contradiction. Additionally, it does not fully disclose other behavioral traits such as permission requirements or side effects beyond tombstoning.

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 three sentences, starting with the core action, then detailing the 'to' options. It is concise and front-loaded, though the version prefix 'v3.1.0 M2' adds minor noise.

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?

Given the tool has 7 parameters and no output schema, the description covers the 'to' options well but omits details about the return value for 'to=decision', side effects, and preconditions. The annotation contradiction also undermines completeness.

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?

The description adds context for key parameters like 'to' (target stores and their status) and 'force' (overrides check_conflict). However, schema coverage is low (43%), and parameters such as tags, context, file_path, and do_not_revert are not explained in the description, leaving gaps in understanding.

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 promotes a working-memory entry to long-term memory and tombstones the source, specifying different behaviors for 'to' targets. It distinguishes itself from siblings by focusing on promotion from working memory, though it does not explicitly contrast with other tools like working_add.

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 provides explicit guidance on when to use each 'to' option: 'to=decision' is fully wired and calls check_conflict, while 'to=skill' and 'to=playbook' are reserved for future milestones and return a deferred response. It also mentions force=true to override conflict checks. However, it lacks general prerequisites or when not to use.

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