guild_brawl_sps_rewards

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

With no annotations, the description carries the full behavioral burden. It does disclose several important behaviors: it makes one logical GET request without auto-fetching continuation pages, locally limits results to 100 rows and 256 KiB with truncation reporting, and refuses oversized records. It also clarifies that filters are forwarded as supplied and their effectiveness is not guaranteed. However, the sentence 'Use the string 1 for include_total or include_cycles: true returned an empty object' is confusing and could mislead an agent about how to set boolean-like parameters, detracting from clarity.

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 verbose and poorly structured. It front-loads the purpose but immediately follows with a confusing, run-on note about parameter usage. Subsequent sentences jump between filtering semantics, request behavior, and output limits without clear organization. The length is not justified by clarity; it could be tightened significantly.

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?

Given no annotations, no output schema, and five parameters, the description needs to be thorough. It does cover request behavior, pagination, limits, and filtering semantics, but it fails to explain the core parameter semantics (especially cycle, start_cycle, end_cycle) and never defines what 'sps_reward_records' is or what the response structure looks like. The description assumes domain knowledge that an agent may not have, leaving critical gaps.

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 0%, so the description must compensate by explaining the parameters. It only mentions include_total and include_cycles, and even then in a confusing way ('Use the string 1 for include_total or include_cycles: true returned an empty object'). It does not explain the meaning of cycle, start_cycle, or end_cycle, leaving most parameters undefined. The hint that 'Cycle records are bounded while a requested total is retained' gives some context but is insufficient.

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 opens with a clear verb and resource: 'Read global brawl SPS payout totals and/or cycle records.' It explicitly uses 'global' to distinguish from guild-specific sums, which helps separate it from siblings like guild_brawl_records. However, it does not explicitly name an alternative tool or state the exact differentiation, so it's clear but not perfectly disambiguated.

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?

There is no explicit guidance on when to use this tool versus alternatives. The description mentions 'The total is global even when cycle narrows records; it is not a guild or selected-cycle sum,' which implies scope but does not say 'use this when you need global totals' or reference any sibling. It also does not describe any prerequisites or fallback conditions, so an agent has to infer the appropriate use case.

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