agtmem_write

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

With no annotations provided, the description carries the full transparency burden. It discloses that superseded notes are kept but marked superseded, which is non-obvious. It implies mutation via 'update' and 'supersedes' but doesn't detail side effects like chunking behavior or scope/global implications. This is a reasonable disclosure for the context.

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 a single, dense paragraph with highly relevant information, front-loading the purpose ('Create or update a note') and prioritizing usage guidance over form. Every sentence adds value: type semantics and supersedes behavior. It avoids fluff and is appropriately concise for a tool with 10 parameters.

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 10 parameters and moderate schema coverage, this description is reasonably complete for a write tool without an output schema. It explains the critical 'type' and 'supersedes' parameters and provides usage scenarios. However, it omits behavior of 'update' flag and how 'scope' affects visibility, but these are less critical for typical use.

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 40%, so the description must compensate. It explains the 'type' parameter semantics (decision, fact, etc.) and supersedes, but doesn't cover many other parameters (id, tags, scope, update, origin, detail) that have minimal schema descriptions. The description adds some value but doesn't fully bridge the gap for all parameters.

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 creates or updates a note, with specific resource ('note') and verb ('Create or update'). It differentiates from siblings like agtmem_search and agtmem_read by focusing on write operations, and distinguishes note types and supersede behavior.

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 guidance on when to use each note type (decision, fact, project, candidate) and how to use supersedes to replace outdated notes. It implies write vs read alternatives (search/read for retrieving) but doesn't explicitly state when not to use this tool compared to append or bug, leaving a minor gap.

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