memory_prepare_compaction

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

Annotations declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the safe read-only nature is already communicated. The description adds value by detailing that output is a string with token counts and that the intended usage is to summarize before compacting, which gives the agent a clearer picture of expected behavior.

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 somewhat lengthy due to the workflow and style guidance, but it is well-organized and front-loaded with the primary purpose. The workflow list makes it scannable, and each sentence contributes useful information, so it earns a 4 rather than a lower score.

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?

The description covers the return type, the full workflow, and important context about how digest content should be written (compressed English, verbatim code/paths/IDs). With no parameters and safe annotations, this is sufficient for the agent to use the tool effectively.

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?

The tool has no parameters and the input schema is empty, so there are no parameter descriptions needed. The baseline for zero-parameter tools is 4, and the description does not attempt to explain any (non-existent) 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 explicitly states that the tool 'Returns cold entries grouped by agent session' and frames it as a preparation step for summarization and compaction. This distinguishes it from sibling tools like memory_compact, which performs the actual archival, by indicating this is the read step before writing a digest.

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?

It provides a numbered workflow: call memory_prepare_compaction, summarize, call memory_write for the digest, then call memory_compact. This makes it clear when to use this tool as the initiation of a compaction sequence, though it does not explicitly list scenarios where it should not be used.

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