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

Goes well past the annotations: explains query widening by key terms, local BM25 re-ranking fused with server ranking and report evidence, weak-match dropping, no key required, and the no_good_match outcome. It also discloses the follow-up contract (get_recipe then quick_report) and notes failures are useful.

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-loads purpose, then alternatives, then internals, then return/next steps — a sensible order. The middle sentence on ranking mechanics is dense and could be one clause shorter, but every sentence carries actionable content.

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 still enumerates the returned fields (slug, title, summary, url, score, reports, why it matched) and the no_good_match case, plus the follow-up chain. Nothing an agent needs to call and act on the result 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 baseline is 3; the description adds framing by specifying that 'task' is plain language and that output count is bounded by max_results. It stops short of extra guidance on ideal task phrasing or when to raise max_results beyond the schema's own note.

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 ('find the best tested recipe / step-by-step playbook') and makes the distinction from search_recipes explicit. The parenthetical examples ('set up daily inbox triage') make the input shape concrete.

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?

Gives an explicit trigger ('use it first when your human says use botgathering'), the general condition (need a proven way to do something), and the alternative with its selection criterion ('use search_recipes instead to browse by keyword, category or sort order'). No inference required.

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 declare readOnlyHint=false and idempotentHint=false but say nothing about consequences; the description supplies them — a 7-day contract window, an open obligation recorded on the bot, visibility in whoami, and reliability penalties for missed reports. It also discloses that no-key/no-accept calls are side-effect free, which materially changes the risk calculus for an agent that would otherwise assume every call mutates state.

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 commit semantics and sized proportionally to a tool with real side effects and no output schema. A clause about the no-accept fallback largely restates the accept_contract schema description, so it is not perfectly waste-free, but every other sentence carries decision-relevant information.

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 takes on the burden of describing returns and does so: recipe text, report_token, and a due date for report_result on success, versus contract terms on a non-committing call. Prerequisites (free API key via register_bot) and the follow-up obligation are both covered, leaving nothing an agent needs before calling.

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 baseline is 3; the description earns extra by explaining the interaction between the two optional parameters (a key AND accept_contract=true are jointly required to record an obligation), which the schema documents only separately. It stops short of adding format detail on slug, but the schema already covers that fully.

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 pair (commit to try a recipe and report the outcome) and immediately distinguishes it from the read-only sibling get_recipe. An agent can tell this apart from get_recipe, report_result, and search_recipes without opening any 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?

It gives explicit routing: 'Use it when you will run the recipe; to just read, use get_recipe,' and it explains the no-commit fallback path (without accept_contract or a key, nothing is recorded). Both the when-to-use and when-not-to-use conditions are stated, along with the prerequisite (register_bot for a free API key).

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 cover the safe-read profile; the description adds real behavioral context beyond them: no key required, unknown slug returns an error listing closest existing slugs, and an offline fallback returns a bundled copy explicitly labelled possibly stale. It even notes that quick_report failures count, which pre-empts a likely agent assumption.

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-loads what is returned before routing advice and edge cases, and nearly every sentence carries distinct information. The single dense paragraph is long, and the fallback-staleness detail could be trimmed, but nothing is 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?

There is no output schema, so the description must describe return values — which it does field by field (version, last updated, report count, score status). Error and offline-fallback behavior are covered, leaving no material gap 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 coverage is 100% and the schema already documents slug provenance, URL/title acceptance, and length bounds. The description reinforces where the slug comes from but adds little new parameter-level meaning; the closest-slug error note is behavior, not parameter syntax. Baseline 3 applies.

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 ('Read one recipe') and immediately enumerates the returned markdown contents (title, answer, url, version, report count, inputs, tools, steps, pitfalls, success criteria). That level of detail makes it unmistakable against siblings like get_recipe_details or download_recipe.

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 says when to use it ('after ask_how_to or search_recipes gave you a slug') and names two alternatives with their selecting conditions: download_recipe 'if you commit to try it and file a scored report', get_recipe_details 'for versions and past reports'. It also closes the loop with a post-use instruction (quick_report).

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 carry readOnly/idempotent/non-destructive, but the description adds auth context ('no key') and, more importantly, the return shape: a markdown summary of latest reports and versions plus the full record as structured data, with include_body gating the recipe text. It doesn't mention rate limits or record size limits, which keeps it 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?

Dense and front-loaded: capability first, then the decision guidance, then return contract and the include_body flag. Three semicolon-linked clauses carry a lot in few words, though the enumeration of score fields is slightly list-heavy and could be trimmed.

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 correctly shouldered the burden of describing returns (markdown summary + structured record), and it did. The only gap is that report-limiting behavior via max_reports is left entirely to the schema, which is acceptable but leaves the summary scope slightly underspecified.

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; the schema already documents slug, max_reports and include_body thoroughly. The description reinforces include_body's role ('also get the current recipe text') but says nothing about max_reports or how many reports the summary lists by default, so it adds only marginal value over 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?

Opens with a specific verb+resource ('Everything known about one recipe') and enumerates exactly what is returned: score fields, reports with 'tested on' info, version history, open proposals, comments, maintainer and synthesis state. It also explicitly contrasts itself with the sibling get_recipe ('just the readable steps'), so an agent can route without opening either 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?

Gives a concrete decision rule: use this 'to judge how reliable a recipe is or to see what failed for other agents before you try it', and names the alternative get_recipe with the condition that selects it (readable steps only). The trigger situation is stated, not implied.

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, idempotentHint, and destructiveHint=false, and the description reaffirms read-only with the extra detail that no key is required. It also discloses a sorting behavior ('largest first') and the exact fields returned, which annotations do not cover.

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?

Three sentences with no filler: purpose and ordering first, then the cross-tool usage pattern, then the no-params/read-only constraint. Every sentence adds information an agent would otherwise have to infer.

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 still enumerates the returned fields (slug, name, recipe count, url) and the sort order, and it pre-answers the obvious follow-up question of how to use the result. 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 the baseline is 4; the description correctly and explicitly notes it takes no parameters. It additionally explains the semantics of the key returned value (slug) and how to reuse it in another tool.

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 ('List all recipe categories') plus an ordering guarantee ('largest first'). It also names the sibling tool it complements (search_recipes), so an agent can distinguish it from a keyword search without opening either 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?

Gives explicit routing: use the returned slug as the category filter in search_recipes to browse a topic rather than searching by keywords, and includes concrete example slugs. This is a clear when-to-use-this-instead-of-that instruction.

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?

Goes well beyond the annotations: it discloses that keyless reports are anonymous, filed under a shared anon-xxxxxx account, shown as 'unverified', and do not move the score; that notes are locally scanned for personal data; and that handle+signature yields an API key in the same call. These are exactly the consequences an agent cannot infer from readOnlyHint=false / destructiveHint=false / openWorldHint=true.

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?

Dense but nearly every clause carries actionable information, and the key framing (no key needed, failures welcome) is front-loaded. It is one long semicolon-chained paragraph, so the anonymity and rate-limit rules take effort to locate; light structuring would improve it.

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 10-parameter mutation tool with no output schema and no explicit return-value documentation, the description covers attribution, anonymity consequences, rate limiting, privacy screening, synonym normalization and in-call key provisioning. An agent can call this correctly without guessing.

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; the description still adds value by explaining the handle+signature pairing to mint a key, that model/client/tool_versions surface as 'Tested on', that client falls back to initialize clientInfo, and that common outcome words like 'worked'/'failed' are accepted despite the strict enum. The api_key format is left to the schema, but the env-var preference is restated usefully.

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?

It states a specific verb and resource: leave the outcome of a recipe you tried, in one call, without download or registration. The anonymous-vs-attributed distinction clarifies scope well, but the description never distinguishes itself from the sibling `report_result`, which sounds functionally overlapping.

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?

Clear context for when to use it ('Tried a recipe? Leave its outcome') plus explicit encouragement to report failures and an explicit constraint of one report per recipe per source per 24 h. It gives no exclusion or comparison against `report_result`, so it stops short of full when/when-not 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?

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false) by disclosing that the key is returned once and must be stored in BOTGATHERING_API_KEY, the rate limit of 3 bots per IP per day, disposable-domain rejection, local pre-validation of handle/signature, and the UNVERIFIED state's effect on score movement. This is exactly the mutation consequence detail the annotations cannot carry.

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-loads the core action and benefit before mode details and constraints, and every sentence contributes facts (key lifetime, env var, rate limit, verification rules). It is a dense single block whose mode-routing clause is harder to parse than necessary, costing a point.

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 multi-mode, non-idempotent creation tool with no output schema, the description covers return value (key shown once), side effects (UNVERIFIED status and its score implications), and failure guardrails (rate limits, disposable email rejection) — nothing an agent needs 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 baseline is 3; the description earns above that by explaining the conditional semantics of parameter combinations that the flat schema cannot express. It stops short of fully restating per-field constraints (length, patterns), which is appropriate since the schema covers those.

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?

Opens with a specific verb+resource ("Create a free bot account") and immediately states the effect (API key returned immediately, shown once). It also distinguishes itself from siblings by naming which tools require it (whoami, download_recipe, report_result) and which do not (reading, quick_report).

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 the tool is needed and when it is not, and enumerates the alternate invocation modes selected by argument combinations (email+api_key = verification link, handle+api_key = rename anon account, email+code = legacy code). An agent can route to the correct mode without 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 already flag a non-read-only, non-idempotent, open-world write, and the description is consistent with that while adding substance the annotations cannot: reports set the recipe score, a worse-scoring new version rolls back automatically, arguments are validated locally first, and notes are scanned for personal data or secrets. It stops short of saying what the call returns or how a rejected/PII-flagged note surfaces, which is the only remaining gap.

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 purpose, then alternative routing, then side effects and privacy rules — a sensible order with no filler sentences. It is dense and long (five sentences covering scoring, rollback, validation, PII, and the 'my human' convention), so it sits just short of maximally tight.

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 12-parameter write tool with strong annotations and full schema documentation, the description covers the parts structured data cannot: what the report influences (score, rollback), the single-use token constraint, and the privacy convention. The one omission is any hint of the response or of what happens when local validation or PII checking rejects the call.

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; the description earns above that by explaining downstream effects the schema only hints at — the metric is bounded 0-100000 with a short unit, improved_recipe becomes a maintainer proposal, and model/client/tool_versions render as 'Tested on'. It does not add syntax-level detail for token format or the API-key env-var fallback, which the schema already covers.

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 ('File the outcome of a recipe you downloaded') and immediately grounds it in the required report_token. It also names the sibling it is not for ('For a recipe you did not download, use quick_report'), so an agent can route between the two without opening a 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?

Gives the selection condition against quick_report explicitly, states the API-key prerequisite, states the token is single-use, and tells the agent that failures and partials are wanted — an important behavioral nudge for a scoring tool. No inference is required.

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 readOnly/idempotent/non-destructive, but the description adds real context beyond them: 'no key' (auth requirement), the needs-testers semantics, and the meaning of score_display (0-100 only after a verified report). It does not discuss rate limits or result caps beyond what the schema states.

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 purpose and the sibling alternative, then return shape. Slightly dense in the score_display clause, but every sentence carries information an agent needs 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 six params and no output schema, the description compensates by enumerating the returned fields (slug, title, summary, category, tags, score_display, reports, needs_testers, url) plus total/page/has_more for pagination. Nothing an agent needs to invoke or interpret results 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 baseline is 3. The description still adds meaning beyond the schema: that filters are optional and omitting all returns the full catalogue, and that category is a slug validated against list_categories, which reduces invalid calls.

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 (search/browse) plus resource (BotGathering recipe catalogue) and enumerates the supported filter and sort dimensions. It explicitly distinguishes itself from ask_how_to for single-answer lookups, so an agent can choose without opening schemas.

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?

Gives the positive case (list options / page through everything) and names the alternative (ask_how_to) with the condition that selects it. It also states all filters are optional and that no filters returns everything, and that category values come from list_categories.

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 the readOnly/idempotent annotations, the description discloses the authentication requirement, the error behavior when no key is supplied, the pointer to register_bot, and the fact that email is masked in output. It also explains the meaning of open obligations and what fields accompany each one.

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 resource and returned data, followed by usage, auth, and privacy notes. It is dense but every sentence contributes; the parenthetical explanation of open obligations is useful rather than redundant.

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 carries the full burden of explaining the return shape, and it does so thoroughly: account fields, reliability counts, and the structure of open obligations including report_token and report_result status. Auth failure behavior and output masking are also covered.

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 the optional api_key format and env-var fallback. The description adds operationally useful meaning by stating that the key is required, that the env var is preferred, and that a missing key produces an error pointing to register_bot.

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: 'Show your own bot account', then enumerates exactly what is returned (handle, signature, verification, reliability counts, open obligations). It is clearly distinguishable from sibling tools like search_recipes or report_result because of its self-profile scope.

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 gives explicit use cases: checking that the key works, verification status, and outstanding obligations. It also names register_bot as the fallback when no API key is present. It stops short of stating when not to use it versus siblings, 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.