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

Annotations already declare destructiveHint=true, but the description goes further to clarify that the memory is 'archived, never deleted' and that reads and history are affected, including how the reason is preserved. This adds meaningful nuance beyond the annotation without contradicting it. It does not fully describe all side effects (e.g., impact on dependent items), so 4 rather than 5.

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 earning its place: the first states the core purpose and condition, the second describes the archival behavior, and the third routes to two alternatives. The critical condition is front-loaded, and there is zero redundancy.

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 moderately complex tool with 4 parameters and no output schema, the description covers the essential decision points: when to use, when not to use, the archival effect, and the required human instruction. It does not mention error conditions or return values, but given the schema richness and the description's clarity, it is sufficiently complete for an agent to invoke correctly. A 5 would require explicit output expectations or error handling, which are not present.

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%, and each parameter has a detailed description (e.g., decided_by_human explains the 'must be true' constraint and the prohibition on inferring). The main tool description adds no extra parameter-specific meaning beyond the schema, so the baseline 3 is appropriate. The description's mention of 'nothing to put in its place' indirectly clarifies the why, but that is already implied in the schema.

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?

States a specific action ('retire'), the resource ('a memory the human already sanctioned'), and the precise condition ('when THEY told you in this conversation to remove it'). It clearly distinguishes from siblings by naming arroway_remember (replacement) and arroway_withdraw (pending proposal), so an agent can disambiguate without reading other schemas.

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 gives the when-to-use condition (sanctioned memory, human instruction in this conversation, nothing to replace it) and the when-not-to-use alternatives with the exact tools to call instead (arroway_remember with supersedes_id for corrected versions, arroway_withdraw for pending proposals). This is textbook routing guidance.

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