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

With no annotations provided, the description carries the behavioral burden. It discloses conditional side effects via 'Get-or-create' and explains the non-obvious slug mapping for harness and cloud agents. It doesn't explicitly state whether an existing profile is ever modified, but 'get-or-create' strongly implies idempotent ensure semantics.

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: purpose, naming convention, and routing to read-only alternatives. The core action is front-loaded and there is no 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 tool with 7 optional parameters and an output schema, the description provides the essential decision context: what it ensures, how slugs are formed, and how other agents should read the profile. An explicit note about when to prefer memory_agent_set instead would make it fully complete, but the schema and output schema cover most remaining mechanics.

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% and each parameter has its own description, establishing a baseline of 3. The description adds extra meaning by tying the name parameter to harness labels and cursor_agent_id to cloud agent slugs, which goes beyond the schema's raw field descriptions.

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 opens with a specific verb and resource: 'Get-or-create this org's ontology Agent + shared memory profile.' This clearly conveys an ensure operation and immediately distinguishes it from read-only siblings like memory_agent_get and memory_entity_view.

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 explicitly routes read-only needs to alternatives: 'Other agents read the profile with memory_agent_get or memory_entity_view.' It also gives useful context on when harness vs cloud agent naming applies. It stops short of explicitly contrasting this with memory_agent_set, but the get-or-create framing largely communicates the intended use.

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