Agent Bounty Feed

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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds the useful detail that ids are namespaced across sources, but says nothing about behavior for unknown/stale ids or what the 'full record' contains.

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?

A single sentence with the resource and the id-source stated up front, followed by compact inline examples. No waste.

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 single-param read tool with annotations and no output schema, the description covers enough to invoke it correctly. The only gap is any hint about what the returned record includes or how errors surface.

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% and the single 'id' parameter has no description, so the description must carry this burden. Three concrete id-format examples (frantic:142, taskmarket:TSK-XXXX, algora:owner/repo#123) do that well, though it doesn't state whether the prefix is mandatory or case-sensitive.

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 ('Full record for one bounty id') and explicitly ties it to list_bounties as the source of ids, which cleanly separates it from list_bounties and get_new_bounties.

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 phrase 'from list_bounties' implies the correct workflow: discover ids first, then fetch details here. It does not state exclusions (e.g. don't use this for bulk fetches), so it falls just 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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds useful behavioral context in naming 'last refresh time' and 'items dropped by verification', which hints at freshness and post-filter counts, but says nothing about cost, caching, or the scope of the aggregate (whole feed vs. filtered view).

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?

A single front-loaded sentence fragment with no filler, listing exactly the metrics returned. The comma-list style is dense but readable and earns its space given there is no output schema.

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?

With no output schema, the field enumeration carries the return-shape burden and does so reasonably, including an unusual 'need no bond/stake/KYC' breakdown. However, terms like 'verification' and 'per-source' are left undefined, and nothing states the aggregate's scope or whether it reflects the full feed.

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 tool takes no parameters and the schema is an empty object, so there is nothing to disambiguate; baseline 4 applies. The description correctly implies the call is parameter-free by framing everything as a fixed totals report.

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 is a bare enumeration of returned metrics rather than a verb+resource statement; an agent infers 'aggregate statistics for the bounty feed' but never gets it said explicitly. It distinguishes itself from the list_bounties/get_bounty siblings implicitly (aggregates vs. records), but not by name.

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 guidance on when to call this versus list_bounties, get_new_bounties, or get_bounty. No mention of whether it is a cheap overview call to make before drilling into individual bounties, or of any precondition.

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 already declare readOnlyHint and openWorldHint, so the description rightly spends its words elsewhere: result ordering, the strict inequality on `since`, and the presence of a next_since cursor in the response. It doesn't mention rate limits or behavior when since is in the future, but the disclosed traits are the ones that matter for a polling feed.

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?

Two sentences, no filler, and the core semantics appear before the polling convention. Everything present 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?

With no output schema, the description supplies the one piece of return-value knowledge an agent needs (next_since) and otherwise relies on a fully documented schema. Nothing required 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?

Schema coverage is 100%, so the schema already documents all seven parameters; the description adds value beyond it by clarifying that `since` is strictly exclusive and that a returned next_since is meant for the next `since` value. That roundtrip contract is not expressed in the schema.

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 resource (bounties), a precise temporal filter (first seen strictly after `since`), and an ordering (newest first). It does not name a sibling to contrast with, so an agent must infer how it differs from list_bounties and get_bounty, but the delta/feed semantics are clear enough.

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 second sentence gives explicit operational guidance: capture `next_since` and pass it on the next call to get only new items, which describes the intended polling workflow. It stops short of stating when to prefer this over list_bounties.

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 already cover the safety profile (readOnlyHint, openWorldHint), and the description adds real value beyond them by disclosing data provenance (Frantic, Taskmarket, Algora/GitHub, etc.) and freshness ('verified hourly'), which affects how much an agent should trust the results. It omits pagination behavior and the audit-contest distinction, which the schema carries instead.

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?

Two sentences, front-loaded with purpose and scope before the field list, with no filler. The parenthetical source enumeration is long but carries real provenance information, so it mostly earns its space.

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?

With no output schema, the description usefully enumerates returned fields (reward, est_usd, url, deadline, requires[], slots_left, competition, payout_track_record), and all seven filters are covered by the schema. The remaining gap is routing guidance against the three sibling tools, which a browse-style feed should still mention.

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 every filter (q, sort, limit, source, min_usd, network, exclude_requires) is already documented in structured data; baseline 3 applies. The description expends its second sentence on returned item fields rather than param semantics, adding little beyond the schema.

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 gives a specific verb and resource ('List currently open, claimable, paid bounties for AI agents') and narrows scope with the source list, so an agent can tell it surfaces filtered listings rather than a single record. It doesn't name sibling tools like get_bounty or get_new_bounties, so the differentiation is inferable rather than stated.

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?

No sentence explains when to call this versus get_new_bounties (newest-first view) or get_bounty (single lookup); the 'currently open' wording implies a browse-style use but never states it. The agent must infer routing from the sibling names alone.

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