capture_activity

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

The description discloses important behavioral details beyond annotations: candidates are queued, not immediately searchable, and only enter recall after user approval at the provided URL. It also warns against sending secrets, credentials, or personal data. These behaviors are not implied by the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false), so the added context is valuable and non-contradictory.

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?

Five concise sentences, each serving a distinct purpose: the action, the invocation condition, the approval behavior, the data-handling restriction, and the alternative tool. The most critical information (what and when) is front-loaded, and there is no redundant or promotional language.

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 only two parameters, no nested objects, and an output schema present, the description fully covers what an agent needs to call the tool correctly: purpose, timing, qualification criteria, post-call behavior, and a non-obvious routing rule. Nothing material is missing.

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 50%: taskId is explained, but activity has no schema description. The tool description compensates by clarifying activity content: it should contain inferred stable stack choices or conventions, not explicit user statements, and must avoid sensitive data. This adds semantic meaning the schema lacks, though it does not describe format details like the maxLength constraints already present 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?

The description begins with a specific verb and resource: 'Queue durable facts inferred from agent activity for the user's review.' It clearly differentiates itself from sibling save_memory by explicitly saying 'Use save_memory instead when the user stated the fact.' The intended use case is also concrete: capturing stable stack choices or conventions that were not explicitly confirmed.

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 states when to use the tool: 'Call after a session produces stable stack choices or conventions the user did not explicitly confirm.' It also names the alternative and the condition that selects it: 'Use save_memory instead when the user stated the fact.' This gives clear routing guidance with no inference required.

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