memshelf_advise

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

Annotations already establish readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description mainly restates that ('writes nothing') and adds the modest detail that an empty occupants list is legal and produces an explicitly degraded report. It does not mention the verification behavior for episode_id claims, which the schema covers instead.

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?

Two dense sentences with the core purpose front-loaded and the fallback case parenthesized at the end; no filler. The em-dash clause stack is slightly compressed but still parseable.

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?

With full annotations, a rich nested schema and an output schema, the agent needs little more than purpose and payload shape, both of which are present. The one gap is that the description never situates this tool among its twelve siblings, which matters for a diagnostic-style tool.

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 top-level schema is only a 'params' wrapper (reported coverage 0%), so the description has to carry semantic load - and it does, mapping the occupant fields to plain language ('label, size, live or not'). The nested definitions are also well documented, so the agent can populate the payload without guessing, though budget/staleness semantics are left entirely to 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?

States a specific verb+resource: it reports the composition of the caller's context window and returns 'ranked proposals' for what to drop, and it explicitly says it 'writes nothing'. That distinguishes it from write-oriented siblings like memshelf_shelve and memshelf_purge. It does not name any sibling directly, so it stops short of top marks.

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 gives a usable usage condition - pass occupants when you want the window side analyzed, omit them and you get the shelf side only - so the agent can infer when to call it. However, it never contrasts itself with the many nearby read siblings (memshelf_stats, memshelf_recall, memshelf_search), so routing between them is left to inference.

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