Session

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

With no annotations, the description must carry the behavioral burden. It does identify the high-level behaviors (recap, verbosity, briefing_order, compress, health) and even implies that compress affects the audit log. However, it does not disclose side effects, reversibility, permissions, or output behavior, particularly for 'compress' which likely mutates or truncates data.

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 two sentences, front-loads the core purpose, uses a compact 'Use when' list, and closes with a clear negative routing rule. Every sentence contributes information and there is no redundant or filler text.

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 is sufficiently complete for selecting and invoking the tool: it covers all actions, the use-case context, and the main alternative tool. Schema descriptions cover all parameters. The main gap is that conditional parameter requirements per action (e.g., mode needed for verbosity, sections for briefing_order) are not explicitly stated, though they can be inferred from the description and schema.

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 100%, so the baseline is 3, but the description adds meaningful context by mapping each action to its purpose: 'setting output verbosity (verbosity)', 'reordering briefing sections (briefing_order)', 'compressing the audit log (compress)'. This clarifies how the action parameter relates to mode, sections, and max_entries beyond the schema's terse descriptions.

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 uses a specific verb ('Manage') with a clear resource ('session-level surfaces and diagnostics') and enumerates all five actions with their purposes. It explicitly distinguishes itself from the story tool via the 'Do NOT use when... use story (action: record)' directive.

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 an explicit 'Use when' list tying each action to its intended scenario, and an explicit 'Do NOT use when' exclusion with the correct alternative tool. This leaves little ambiguity about when to select this tool over siblings.

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