copilot_export_memory

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds the useful pagination trait ('bounded page'), but says nothing about volume, what 'relationship memory' contains, or whether 'export' returns inline data versus writing a file.

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?

A single front-loaded sentence with the resource and its bounding constraints up front. Nothing extraneous and no restatement of the name.

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 read-only export with no output schema and an ambiguous verb, the description should clarify the return shape, page-size limits, and termination condition. It hints at paging but leaves the critical question of what an export actually yields unanswered.

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 0%, so the description must carry parameter meaning; it only conveys that domain selects one partition and that results are paged. It gives no defaults, no maximum for limit, and no offset semantics, leaving the agent to infer all three 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?

Specific verb ('Export') plus resource ('relationship memory') plus scope ('one bounded page', 'single domain') tells an agent exactly what it gets. It is distinguishable from siblings like copilot_get_activity and copilot_sync, though it does not explicitly name them.

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?

'One bounded page ... for a single domain' implies the caller iterates with limit/offset and partitions by domain, so the usage pattern is inferable. However, there is no explicit when-to-use, no mention of alternatives such as copilot_get_activity, and no statement about whether export should be repeated until exhausted.

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