Delimit Cost Controls

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

The description clearly discloses side effects ('action="set" / "reset" mutate the rate-limiter state'), which is excellent transparency in isolation. However, this directly contradicts the annotation readOnlyHint=true, which claims the tool makes no modifications. This is the same pattern as the create_record calibration example: a description claiming write operations while annotations declare read-only. The conflicting signals leave the agent unsure whether invoking this tool is safe.

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?

Well-structured with labeled sections (When to use, When NOT to use, Sibling contrast, Side effects) that make it easily scannable. Every sentence earns its place, and the most decision-relevant information is front-loaded. The format is exemplary for an agent-facing definition.

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 purpose, usage boundaries, sibling differentiation, and per-action side effects. An output schema exists, so return values don't need describing. Minor gaps: it doesn't distinguish what 'status' vs 'quota' actions each return, and the annotation contradiction undermines the otherwise complete safety picture. Still, nearly everything needed to call it correctly is present.

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 baseline is 3. The description's phrases ('per-tool hourly rate limits', 'session cost cap') reinforce the mapping to limit/cost_cap, and the side-effects section adds action-level semantics (which actions mutate vs read). But this largely restates what the schema already documents rather than adding meaningful new parameter meaning.

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 opening line 'Manage MCP rate limits and session cost controls' uses a specific verb and resource, and the scope is unmistakable. It also distinguishes itself from siblings by explaining that delimit_cost_analyze inspects project spend while this manages per-session call quotas. An agent can clearly tell what this tool is for.

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 explicitly states 'When to use', 'When NOT to use', and names the alternative tools (delimit_cost_analyze for project-cost analysis, delimit_cost_alert for alert configuration). The sibling contrast section further reinforces the decision boundary. No inference is required to choose correctly between this and related tools.

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