zooidfund

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

With no annotations, description fully covers prerequisites (auth, operator_acknowledgement=true) and explicitly lists what it does NOT do (KYC, identity verification, key recovery). Could improve by noting success/error behavior.

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?

Compact, well-organized sentences. No wasted words; each sentence adds critical information (action, auth, usage condition, warning, exclusions).

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 simple parameter schema and tool complexity, description covers all essential aspects: purpose, conditions, prerequisites, and limitations. No obvious 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 100%, but description adds value by explaining the parameter's meaning ('explicit operator authorization') and linking to the required URLs. Justifies the const=true constraint.

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?

Clear verb 'Record acceptance' and specific resource 'current Agent Operator Acknowledgement for an already registered agent'. Distinct from sibling tools that handle donations, campaigns, etc.

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?

Explicitly states when to use: 'Use this if get_evidence returns operator_acknowledgement_required.' Also warns against automatic invocation, providing clear usage boundaries.

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

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

No annotations exist, so the description carries the full burden and does so: it discloses validation gates (network check, confirmed receipt, duplicate tx_hash replay protection, sender/recipient/amount matching), non-obvious traits like relayer top-level senders and bundler-multiple-UserOperation edge cases, and concrete side effects (records donation, increments campaign funded_amount, returns donation_id/status/tx_hash).

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?

Despite being a dense paragraph, it is front-loaded with flow position and required inputs, and every sentence supplies a distinct constraint (replay, relayer, bundler, mismatch handling, side effects). Some edge-case sentences could be split for scannability but none are 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?

For a high-complexity mutation tool with no annotations and no output schema, the description covers validation preconditions, failure modes, side effects, and return fields — everything an agent needs to invoke it correctly and interpret the result. Only caller auth/permissions are unstated.

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 50% — amount and tx_hash have no schema descriptions — but the text compensates: tx_hash must be the actual chain transaction hash, is subject to one-record-per-hash replay protection, and amount must equal the matched Transfer event amount. campaign_id is only lightly reinforced ('correction' caveat) and relies on the schema for its format.

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 names a specific action ('Step 2 of the MCP donation flow') and spells out exactly what the tool verifies and records: network, receipt, replay protection, canonical USDC Transfer event, then recording the donation and incrementing funded_amount. It implicitly separates itself from the sibling 'donate' by framing itself as step 2, though it never names that sibling outright.

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?

Strong exclusion guidance: it says a different transfer already in a recorded transaction 'cannot be recorded through this tool' and instructs the agent to reconcile and report rather than resend. What's missing is an explicit pointer to the sibling 'donate' as the step-1 prerequisite or to 'get_campaign_donations' for reconciliation.

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

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

With no annotations, the description carries the full burden and does well: it discloses that despite the name 'donate' no donation is recorded, that eligibility is validated, and it enumerates the returned payment fields (wallet_address, amount, network, currency). It omits what happens when a campaign is ineligible (error shape) and any auth or rate-limit constraints, so it falls short of a 5.

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?

Four tight sentences, front-loaded with the flow position and the crucial non-recording caveat, then inputs, then return values, then the next step. Every sentence earns its place.

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?

No output schema exists, yet the description compensates by listing the returned payment fields, and it fully documents the two-step workflow an agent must follow. Nothing needed to invoke this correctly is missing.

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 description names the three required inputs but adds no meaning beyond the schema, which already documents campaign_id (full UUID, no abbreviation) and reasoning (public-facing, exclude restricted evidence). At 67% coverage the schema is doing the heavy lifting, so baseline 3 is appropriate.

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 and resource (validates campaign eligibility and issues payment instructions) and explicitly scopes itself as 'Step 1 of the MCP donation flow' that 'does not record any donation yet.' This clearly separates it from confirm_donation, the sibling that completes the flow.

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?

Explicit sequencing: call this first, send the on-chain payment, then call confirm_donation with the same campaign_id, amount, reasoning plus the tx_hash. Both the when-to-use and the hand-off alternative are named, leaving nothing to inference.

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

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

Annotations only declare readOnlyHint=true, while the description adds substantial behavioral context: returned fields, read-time snapshot semantics for evidence counts, deprecated legacy status, append-only unverified campaign_updates, exclusion of creator_email, and verification caveats. It also clearly discloses what the factual fields do not assess.

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 front-loaded with purpose, required input, and return fields, and most sentences add useful context. It is somewhat verbose because the final verification disclaimers repeat the same idea in several sentences, but the overall structure remains efficient.

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?

There is no output schema, so the description must carry return-value and behavioral context; it does so thoroughly by naming returned fields, describing funding_progress and evidence_summary, explaining evidence count semantics, and disclosing caveats. Given the simple one-parameter read operation, an agent has enough information to invoke and interpret it correctly.

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% and the single parameter already has a clear description requiring the full campaign_id UUID. The description repeats that campaign_id is required but adds no extra syntax, format, or validation detail beyond the schema, so baseline 3 is appropriate.

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 and resource: fetching complete detail for one campaign. It distinguishes the tool from search_campaigns by emphasizing a single campaign and full detail, and it enumerates the returned fields so an agent knows this is a detail lookup rather than a search or donation/evidence listing.

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 states the required input and that the tool returns one campaign's complete detail, which implies use after finding a campaign_id. However, it does not explicitly say when to use this versus search_campaigns, get_campaign_donations, or get_evidence, and it provides no exclusions or routing guidance.

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

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

The description adds substantial behavioral context beyond the readOnlyHint annotation: it explains pagination, partial result sets, the presence of has_more and next_offset, and the need to loop until has_more is false. This is important operational guidance for an agent invoking the tool. It does not cover authentication or rate limits, but for this tool the pagination behavior is the critical disclosure.

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 front-loaded with the tool's purpose, but it repeats itself: the first and third sentences both state that donations include the donating agent's identity and reasoning. The pagination guidance is useful but also somewhat repetitive. Removing the redundant sentence would make the definition tighter.

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 that there is no output schema, the description does a good job explaining what the response contains: donation history, agent identity, reasoning, pagination metadata, and the possibility of incomplete results. It does not describe limit behavior or ordering, but it provides enough for an agent to invoke and paginate correctly.

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 only 33%, so the description must compensate for undocumented parameters. It partially does so by explaining offset usage through next_offset, but it does not explain the limit parameter at all. The campaign_id parameter is already documented in the schema, so the description's marginal value is limited to offset 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 clearly states a specific verb and resource: it returns donation history for a given campaign. It also highlights that the result includes donating agents and their reasoning, which distinguishes it from a general campaign lookup. It stops short of naming a sibling tool, but the resource is specific enough for an agent to identify the right tool.

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 a clear use case: 'Use this to understand how other agents have evaluated this campaign.' However, it does not state when not to use this tool or explicitly compare it with alternatives like get_campaign or search_campaigns. The guidance is implied rather than fully specified.

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

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

With no annotations provided, the description carries the full burden and excels: it discloses eligibility checks, pricing-dependent return shapes (evidence_documents vs. x402 handoff), tombstone behavior for deleted evidence, signed_url expiration, and the recommendation to use signed_url over file_reference. This is exceptionally transparent.

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 lengthy but logically structured: it starts with the core action, then prerequisites, then conditional return shapes, then tombstone details. The front-loading is good, but the verbosity and repetition of some details (e.g., listing available fields) prevent a perfect score.

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?

Without an output schema, the description must fully explain return values, and it does: it details the eligibility response, the evidence document structure, the x402 handoff shape, tombstones, signed_url expiration, and even agent responsibilities for retained copies. Nothing critical is missing for correct invocation.

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%, and the schema already provides a descriptive note about campaign_id (full UUID from search_campaigns, do not abbreviate). The description adds no new parameter-specific meaning beyond what the schema supplies, so the baseline of 3 is appropriate.

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: 'Fetch evidence documents for one campaign.' It unambiguously identifies the tool's purpose and distinguishes it from siblings like get_campaign or get_campaign_donations by focusing on evidence documents specifically for a single campaign.

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 provides clear context and prerequisites: it explicitly states the requirement to have accepted the Agent Operator Acknowledgement and the eligibility based on donation volume. However, it does not explicitly mention when to prefer this over alternative tools or provide exclusions for other campaign-related tools, so it stops short of a 5.

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

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

readOnlyHint=true already tells the agent this is a safe read, so the bar is lower. The description adds meaningful context by specifying that results are aggregates and listing which dimensions are summarized, which helps an agent reason about the payload shape despite no output schema.

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?

Front-loaded with the purpose, followed immediately by usage context, then the parameter note. Three compact sentences with no wasted language.

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?

No output schema exists, yet the description covers the return content by naming the aggregate metrics, so an agent knows what it gets back. Combined with the read-only annotation, nothing needed to call it correctly is missing.

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?

Zero parameters, so baseline is 4. The description's 'No parameters required' explicitly confirms what the empty schema already implies, leaving no ambiguity.

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 ('Returns') and resource ('aggregate platform statistics'), then enumerates the concrete metrics (campaign counts, category distribution, donation totals, funding gaps). This clearly separates it from the record-level siblings like get_campaign and search_campaigns.

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?

'Use this before search_campaigns' gives explicit sequencing guidance against a named sibling, a strong signal. It stops short of stating when NOT to use it or ruling out the other siblings (get_campaign, get_campaign_donations), but the intended context is clear.

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

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

No annotations provided, so description carries full burden. It discloses that registration requires explicit authorization, proxies to external function, validates wallet_address format, and returns agent_id and api_key. Also outlines operator responsibilities.

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?

Description is detailed but each sentence contributes value. It front-loads purpose, then lists inputs with context. Could be slightly shorter, but overall well-structured and informative.

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 output schema, description includes return fields (agent_id, api_key). Covers purpose, inputs, constraints, and authorization. Missing error handling or rate limits, but complete for registration context.

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 low (13%), but description compensates by listing all parameters, specifying required vs optional, and adding constraints (wallet_address format, operator_acknowledgement must be true). Adds meaning beyond schema for most parameters.

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 clearly states 'Register a new agent' with specific verb and resource. It distinguishes from siblings by mentioning required operator_acknowledgement and proxying to auth-register, which is unique among sibling tools.

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?

Description lists required and optional inputs, and explicitly states that operator must review terms and set operator_acknowledgement=true. Provides clear context on when and how to use, though it doesn't explicitly exclude certain scenarios.

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

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

Beyond readOnlyHint, it discloses that evidence counts are read-time snapshots that can change, that factual fields do not imply quality or completeness, and that the platform does not verify campaign accuracy. These are meaningful behavioral and trust caveats an agent needs.

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 long but front-loads the core purpose, then groups filters, sorting, pagination, response, and caveats. A few pagination and liability statements repeat slightly, but the length is justified by the 14-parameter surface.

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?

For a 14-parameter search tool with no output schema, it covers the purpose, filter set, enum values, sorting, pagination mechanics, response shape (campaigns, total_matching, has_more, next_offset), and trust limitations. An agent can call it correctly and page through results without further guidance.

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?

With only 7% schema description coverage, the description does substantial work: it lists filters, enumerates category values, gives the country code format, documents sort_by/sort_order, and specifies limit/offset defaults and caps. Some parameters such as min_funding_gap, max_funded_percent, and verified_only still lack semantic detail.

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 first sentence states a specific verb (search), resource (public campaign records), and scope (filters, sorting, pagination). This clearly distinguishes it from get_campaign and get_campaign_donations without needing to open the schema.

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 explains how to use pagination (continue with offset=next_offset until has_more is false) and explicitly deprecates evidence_layer_status. It does not name sibling alternatives such as get_campaign for single-record retrieval, but the search-vs-fetch distinction is clear.

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