Delimit Toolcard Cache

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

The description explicitly states that actions like 'register', 'clear', and 'flush' mutate the cache, and that only 'status', 'delta', and 'estimate' are read-only. This directly contradicts the annotation readOnlyHint=true, which declares the entire tool read-only. The 'clear'/'flush' actions also sit awkwardly with destructiveHint=false.

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 well-structured with a front-loaded one-sentence purpose, followed by compact labeled sections for when to use, when not to use, sibling contrast, and side effects. Every sentence earns its place with 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?

The description covers the main usage context, exclusions, sibling distinction, and side effects, and the output schema plus full parameter coverage reduce the need for return-value details. However, the direct contradiction between the stated mutating side effects and the readOnlyHint=true annotation leaves an agent unable to trust the tool's safety profile.

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 100%, so the input schema already documents all three parameters and their purposes. The description adds some value by labeling which actions are mutating vs read-only and clarifying the cache side-channel nature, but it does not add significant new parameter-level semantics.

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 states a specific verb ('Manage'), a concrete resource ('tool-schema cache'), and a clear objective ('reduce per-session token waste'). It also distinguishes itself from delimit_help, so an agent can tell them apart.

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 gives explicit 'When to use' and 'When NOT to use' guidance, including a concrete use case (repeated dumps, sending diffs) and a clear exclusion (runtime tool dispatcher). It also names the sibling alternative delimit_help for contrast.

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