clickd

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

Annotations already cover the read-only and closed-world profile, and the description adds material context beyond them: failure cases (site never read, draft, answers not found), the remediation path (clickd_rescan reads it), and the auth requirement ('Works with no key'). That is precisely the extra behavioral layer annotations cannot express.

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 When/Instead/Inputs/Returns/Fails in a predictable labelled order, with zero filler. The telegraphic phrasing ('Fails: a site never read, or a draft, answers not found') is slightly compressed to the point of ambiguity, which keeps it just short of top marks.

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 carries return-value disclosure itself and does so for both formats. Combined with inputs, failure modes, remediation and sibling routing, an agent has everything needed to call this correctly on the first attempt.

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, but the description goes further by defining what each format value actually yields: markdown returns the whole list as Markdown text, steps returns the four highest-value fixes with pages, points and a hand-off prompt. This adds selection meaning beyond the bare enum values.

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 ('Gets a site's fixes as a work order') and enumerates the content: what to fix, order, how, why, which pages. That framing makes it clearly distinct from clickd_site (score) and clickd_todo (single next fix), which the description names explicitly.

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 'When' clause ties invocation to the start of site work and to a completed read signalled by clickd_changes. The 'Instead' clause names two alternative siblings and the condition that selects each, so routing is unambiguous.

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 and openWorldHint; the description goes well beyond by enumerating the return shape (host, run, changes, visits, job{id,state,ahead}), the auth requirement ('Needs a key'), and specific failure modes (never-read site or job for another site returns not found). This is unusually complete behavioral disclosure for a read-only tool.

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?

Organized into When/Instead/Inputs/Returns/Fails with the core purpose front-loaded in the first sentence. The telegraphic style is dense but every line carries distinct information; nothing is 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?

With no output schema, the Returns section fully carries the burden of describing return values, and the Fails section covers error behavior. For a two-parameter read tool, an agent has everything needed to invoke it correctly and interpret the result.

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 already 100%, so the baseline is 3. The description adds real meaning beyond the schema: `site` is a domain like example.com, and `job` is the id returned by clickd_rescan, with the important semantic note that changes stay null until the read is done.

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: 'says what a site's latest read changed against the one before,' then enumerates the change categories (score, rules, pages). It also names the two siblings it is not (clickd_rescan, clickd_site), making disambiguation immediate.

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 'When' line gives an explicit trigger and cadence (after clickd_rescan, poll every minute or two with its job), and the 'Instead' line routes to clickd_rescan for requesting a read and clickd_site for the current report. Both alternatives and the condition selecting them are stated.

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, and the description goes well beyond them: private addresses are refused, robots.txt is obeyed, the free tools' hourly allowance applies, and no key is needed. The 'Returns' and 'Fails' lines tell the agent what comes back and what the failure modes are.

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 core action, then organized under When/Instead/Inputs/Returns/Fails labels so each sentence is scannable. No filler beyond the brief 'as the free tools do' framing.

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 compensates by describing the return shape (findings with a one-word state and remediation). Failure behavior, rate limits, and auth requirements are all covered, so an agent has everything needed to call 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%, so the enum and url are already documented; the description still adds real meaning by specifying that ssl consumes only the host portion and locations expects the brand's site rather than a page. Those per-kind input quirks are not derivable from the schema alone.

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 with scope qualifiers: 'Checks one live address now' and enumerates the five check kinds. The word 'one' plus 'now' distinguishes it from the batch-oriented siblings without requiring the schema to be opened.

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 'When:' line scopes it to before/after a fix on a single page, link or host, and an explicit 'Instead:' line routes whole-site checks to clickd_rescan/clickd_changes and last-read snapshots to clickd_pages. Both the use case and the exclusions are named.

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 readOnlyHint=true and openWorldHint=false, and the description adds real value on top: it is free, it requires a key and a claim, and the 'Fails:' line warns rows stays empty until a lookup exists. It stops short of explaining what a 'claim' entails or how credits are consumed.

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?

Labeled sections (When / Instead / Inputs / Returns / Fails) with the core purpose front-loaded and no filler. Every line carries distinct information an agent needs, including the return field list that no output schema supplies.

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 compensates by naming the return fields (host, rows, credits, price, perDay, note) and by covering the auth prerequisite and empty-rows failure mode. Minor gap: 'needs a key and a claim' is asserted without saying how to obtain or verify either.

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 single parameter is already documented as a domain such as example.com; the description's 'Inputs:' line restates the same example. With the schema doing the work, this is the baseline case.

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 ('Lists what assistants were found to cite for a site, question by question') plus the scope constraint ('from lookups already made') and secondary output (credits left). It also explicitly separates itself from clickd_site by noting that page quality is not the same as being cited.

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 'When:' line gives the concrete decision context (tell a person whether assistants cite their site, at no cost) and the 'Instead:' line names the sibling clickd_site along with why it is the wrong choice. Both the trigger and the alternative are explicit.

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 by disclosing auth requirements ('Needs a person's key') and two concrete failure modes: check before proof propagates returns claimed false, and DNS records can take minutes to appear. Annotations only say readOnly=false, destructive=false, openWorld=true; the description supplies the operational nuance an agent needs to avoid misinterpreting a false result.

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?

Labeled sections (When/Instead/Inputs/Returns/Fails) front-load purpose and keep each line load-bearing. The telegraphic phrasing is dense but not wasted, and nothing is buried at the end.

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 compensates by enumerating both return shapes (start: site, record, dns, file, note; check: site, claimed, how). Combined with the failure-mode and auth notes, an agent has everything needed to sequence the two-step flow 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%, so baseline is 3, but the description adds real meaning: it ties `start` to producing a record/file and `check` to verifying and adding the site, and clarifies `site` is a bare domain like example.com. This is substantive semantics beyond the enum labels, though it stops short of exhaustive per-parameter 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?

States a specific verb and resource ('Claims a site for the person') and immediately explains the mechanism: a TXT record or file as proof, then a verification check. The two-phase nature is spelled out, which distinguishes it from every read-only sibling in the list.

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 'When:' clause ties it to private site data (rivals, citations, proposals), and 'Instead:' clauses route to clickd_signup for a key and clickd_site for public reports that need no claim. Both the use condition and the alternatives are named outright.

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=false, so the description's real contribution is elsewhere: it discloses that small crowds return an empty board, that drafts and closed sites are excluded from ranking, and that no key is needed. That is genuine behavioral context beyond the annotations, though it stops short of anything about result ordering or freshness beyond 'latest score'.

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?

Labeled sections (When, Instead, Inputs, Returns, Fails) make it scannable, and the purpose sentence is front-loaded. Every line carries distinct information with no restatement of the name or title.

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?

Seven optional parameters, two enums, and no output schema, yet the description covers filtering, the record variant, paging, the returned fields (total, offset, limit, sites, tiers, note), and failure modes. Nothing an agent needs in order to call 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?

Schema coverage is 100%, so baseline is 3, but the description earns more: it explains that the filters combine 'together or alone', that city requires state, that record substitutes a single record for the place list, and that limit/offset page the board. These are interaction rules the schema does not state.

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 ('Lists the public leaderboard') plus the three shapes it can take: all ranked sites, one crowd's board, or a single record. The 'Instead' line explicitly separates it from clickd_site and clickd_rivals, so an agent can route 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?

An explicit 'When' clause gives the triggering intent ('show a person where a site places among every site, or sites like it') and an 'Instead' clause names both alternatives with the condition that selects them. 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?

Goes well past the annotations: discloses the auth requirement ('Needs a person's key'), the cross-account failure mode ('a proposal or task not the person's keeps nothing and says so'), the return fields, and a privacy constraint ('Never send private data'). Annotations only say it is a non-destructive write with openWorld=false; the description supplies the why-and-what-happens 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?

Labeled sections (When, Instead, Inputs, Returns, Fails) with the primary action front-loaded; every line carries distinct information and there is no filler or repetition of the title.

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 an 8-parameter write tool with no output schema, the description still covers trigger timing, alternatives, the meaning of each non-obvious parameter, the return shape, the failure case, and the auth prerequisite. Nothing an agent needs 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 baseline is 3, but the description adds cross-tool semantics the schema lacks: `proposal` names the proposal carried out (pointer to clickd_propose) and `task` the queued task finished, plus the comma-separated convention for `files` and `rules`. It does not restate the enum values in full, 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?

Specific verb+resource: 'Records a step of work on a site', immediately narrowed to 'what you planned, changed or checked, or where you got stuck'. That framing plus the named siblings (clickd_propose, clickd_todo) makes it unmistakable against the rest of the clickd family.

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?

An explicit 'When:' clause (after each step, including steps that carry out a proposal or queued task) and an explicit 'Instead:' clause routing to clickd_propose for deploy approval and clickd_todo for waiting tasks. When-to-use, when-to-use-something-else, and the alternatives are all named.

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 past the readOnlyHint/openWorldHint annotations by stating auth requirements ('Needs a key; any key reads a public site') and failure behavior ('a site or page not read answers not found'). It also discloses the important override rule that `path` causes the other filters to be ignored. Minor gap: no note on result size or rate behavior, but the safety and error profile is covered.

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, then organized under When / Instead / Inputs / Returns / Fails labels. The telegraphic style is dense but every clause carries information — no filler sentences.

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 tool with no output schema, the description compensates by enumerating the actual return fields (host, run, total, pages; path, status, failing, needsAPerson, linkedFrom, linksTo, quoted) and covering both error and auth conditions. Nothing essential for a correct call 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, but the description adds genuine semantics beyond the schema: it groups params by function (narrow / order / page) and, critically, explains that supplying `path` makes the remaining parameters irrelevant. That interaction is invisible in the schema alone.

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 (listing a site's pages from its latest read) and goes further by disclosing the dual mode: a filtered list, or one page in full when `path` is supplied. An agent can distinguish this from clickd_check or clickd_brief 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?

The 'When / Instead' structure names explicit alternatives with the condition that selects each: clickd_brief for ordered fixes, clickd_check for a page as it is live now. Both when-to-use and when-to-use-something-else are covered.

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 annotation, it discloses authentication requirements, mutual-exclusion failure behavior, not-found behavior, and the existence of a promise in the response. It also explains that deploy should only proceed once this tool says approved.

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 and organized with When, Instead, Inputs, Returns, and Fails sections. Every line adds operational value, and there is no 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 two-optional-parameter read tool with no output schema, the description covers selection semantics, return shape, failure cases, auth needs, and timing. An agent has enough information to call it correctly without needing additional 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 100%, so the schema already defines id and site, but the description adds meaningful constraints: id and site are mutually exclusive, neither means every proposal, and site also returns that site's mode. This goes beyond the schema without being fully exhaustive about value ranges or formats.

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: lists proposals, either all, by id, or by site, and includes site approval mode. It distinguishes this from sibling tools by naming clickd_propose for creating proposals and clickd_todo for the work itself.

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 timing guidance: use before work on a claimed site and repeatedly after clickd_propose until answered. It also names alternatives directly, routing creation to clickd_propose and work details to clickd_todo.

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: discloses the email/approval workflow, the 72-hour link expiry, that `diff` is 'shown and never applied', the auth requirement ('Needs a person's key'), the 20-per-site-per-hour limit, and the failure mode for an unclaimed site. The only gap is the return payload's `note` and `promise` fields, which are named but not explained.

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 labeled blocks (When/Instead/Inputs/Returns/Fails) that make scanning easy and contain no filler. The telegraphic, fragment-heavy prose costs it a point, since '20 proposals a site an hour at most' takes a moment to parse.

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 carries the return burden and does so ('proposal ({ id, state, deploy, ... }), note and promise'), while also covering auth, rate limits, and failure cases. An agent has everything needed to call this 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 already 100%, so the baseline is 3, but the description adds meaning the schema lacks: `diff` is never applied, `pages` is comma separated, and `rule` is 'the rule id it answers'. That extra semantic layer justifies moving above baseline.

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 ('Proposes a change before you deploy it') plus the mechanism: an email with Approve/Decline links that lapse in 72 hours. That mechanism alone distinguishes it from the sibling clickd_proposals, which merely lists or waits on proposals.

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 'When:' clause (before each deploy to a site clickd_proposals says is set to approve) and an 'Instead:' clause naming two alternatives with the exact conditions that select them (clickd_proposals to wait for the answer, clickd_log_work to record the work once done).

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 annotations, it discloses the queuing semantics (added=false when a read is already in line), the ten-minute per-site throttle via allowedAt, refusal of private addresses, and that an API key is required. These are exactly the behaviors an agent cannot infer from readOnlyHint/openWorldHint.

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?

Labeled sections (When / Instead / Inputs / Returns / Fails) front-load the action and routing decision, and every line carries distinct information with no 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, and the description compensates by naming the returned fields (job, added, allowedAt, ahead) plus the two failure modes. For a two-parameter job-creation tool this leaves nothing material an agent needs 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 100%, so both parameters are already documented. The description restates site as a domain like example.com and reason as 'what was changed, in a few words' with no added format, length, or required/optional detail. Baseline 3 applies when the schema does the work.

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?

Uses a specific verb+resource ('puts a fresh read of a site in line') and immediately states it returns a job handle to follow. This clearly separates it from the read-inspection siblings and from a synchronous page check.

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 gives the trigger conditions ('once a fix is deployed, or for a site clickd has never read') and names two alternatives with the condition that selects each: clickd_changes for a queued job's results, clickd_check for a single live page with no read.

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 readOnlyHint/openWorldHint annotations, the description discloses fallback behavior for each view (local/nearby/elsewhere, sites, rules, ahead/behind, pages) and two concrete failure modes: a site with no meaning yet returns found/embedded false, and rules/content without `with` asks for it. It also states the authorization requirement ("Needs a key and a claim"), 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?

Tightly front-loaded with labeled sections (When, Instead, Inputs, Returns, Fails) and no filler. However, some lines are compressed to the point of ambiguity, notably the Returns enumeration ("local, nearby and elsewhere; sites; rules; ahead and behind; or pages"), which costs a parsing pass it need not have.

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 return-value burden and does list the shapes per view, plus failure and auth conditions. The return enumeration and the phrase "kept reads" remain underspecified for a tool whose view-dependent output varies substantially, so a caller may still not know exactly what to expect from market or content views.

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, but the description meaningfully exceeds the schema by explaining what each enum value means functionally — competitors as "rivals doing similar work", near as "closest in meaning", market as "rule by rule", rules/content as "two sites side by side" — whereas the schema only repeats the enum labels. It also clarifies `with` has a default interpretation (rules when used alone), information absent from 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 conveys a specific verb and resource (compare a site against its rivals) and enumerates what the comparison yields: who the rivals are, how close they are, and where the site is behind. It also names the siblings it is not (clickd_leaderboard, clickd_site). The core action is stated somewhat metaphorically ("sets a site against", "from kept reads", "where it is behind"), so the agent must work a little to confirm the semantics, which keeps it off a 5.

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 an explicit "When:" clause (picking fixes that matter relative to the sites a buyer compares it with) and an explicit "Instead:" clause naming both alternatives plus the condition that selects each — leaderboard for rank among all sites, site for its own score. It also states the follow-up behavior for the rules/content views (supply `with`).

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=false, so the safety profile is covered. The description adds value beyond that: 'Fails: nothing to refuse. Works with no key.' tells the agent there are no auth requirements or failure modes, which is not in the structured data. Minor gap only on caching/freshness of the rulebook.

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?

Labeled lines (When / Instead / Inputs / Returns / Fails) are front-loaded and scannable, with no wasted prose. The 'Returns' line mildly restates the opening sentence's field list, a small redundancy.

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, and the description compensates by enumerating the returned fields (id, title, stage, weight, fix). Inputs, failure behavior, auth requirements, and sibling alternatives are all covered, leaving nothing an agent needs in order to call 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?

Zero-parameter tool, so the baseline is 4; the description's explicit 'Inputs: none.' confirms the empty schema rather than adding semantics beyond it. Nothing more could reasonably be said about zero 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?

States a specific verb (lists) and resource (the rulebook / every rule clickd checks) plus the exact fields returned. The sibling contrast lines make it distinguishable from clickd_brief and clickd_pages 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?

Explicit 'When:' clause names two concrete situations (explaining a fix to a person, finding a rule's id), and the 'Instead:' clause routes to clickd_brief and clickd_pages with the exact condition that selects each. Nothing is left 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 give readOnlyHint=true and openWorldHint=false; the description adds material context beyond them: no network fetch, no API key required ("Works with no key"), the returned keys (jsonld, script, missing, problems, recommended, fields), and the failure behavior for an unsupported type. Nothing contradicts readOnlyHint — the tool generates output rather than persisting it.

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?

Terse labeled sections (When / Instead / Inputs / Returns / Fails) front-load the purpose and alternative before any parameter detail. Every line carries information — no filler, no restatement of the title.

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 3-parameter generator with no output schema, the description covers what it produces, the exact return keys, the error path, and the no-auth condition. An agent has everything needed to call it correctly on the first attempt.

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, but the description adds real meaning: `type` must be one of the offered enum values, `as` narrows to a concrete subtype like Plumber, and `fields` takes values by key as text with "Give only what the page shows." It also explains the non-obvious pattern of calling with only the required `type` to discover fields.

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 artifact: "Makes JSON-LD for one page from the fields given, ready to paste." It also bounds scope with "fetches nothing" and explicitly separates itself from the sibling clickd_check, so an agent can pick it without opening 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?

Uses explicit When/Instead structure: use it "to write the structured data a fix asks for," and use clickd_check with kind product for checking a live product page. It also gives a discovery trick ("call it with only type to see the fields") that no alternative tool provides.

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 past the annotations (which only say non-readonly, non-destructive, closed-world) by disclosing that the key is shown once and is unrecoverable, the return fields (key, connect, next, plus email vs anonymous), the failure cases ('an email already signed up, or not an email, says so'), and the rate limit ('three an hour from one address'). It even flags that a throwaway key has a reduced read allowance.

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?

Labeled lines (When / Instead / Inputs / Returns / Fails) make it skimmable and front-loaded, with no filler sentences. The occasional garbled phrase ('the person's by email', 'reads and asks for a few reads an hour') costs a little clarity but no whole sentence is wasted.

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, yet the description enumerates the returned fields (key, connect, next, and whether the key is email-tied or anonymous), states the one-chance display constraint, lists failure modes, and gives the rate limit. An agent has everything needed to call it and to decide what to do on success or failure.

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 says almost verbatim that email is the person's address and should be omitted for a throwaway key. The description reinforces the effect of omitting it but adds no new syntax, validation, or format detail beyond the schema — baseline 3 is appropriate when the schema does the work.

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 ('Gets a free key, shown once') plus the immediate follow-on artifact (the connect command), and distinguishes the two issuing modes (by email vs throwaway). It also names the sibling it is not — clickd_claim — so an agent can separate key issuance from site claiming 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?

Explicit 'When: when a call needs a key and there is none' covers the trigger, and 'Instead: clickd_claim, with a person's key, to make a site theirs' names the alternative and the condition that selects it. It also states a precondition ('Needs no key'), which is exactly the routing information an agent needs.

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=false, yet the description still adds real context: it reads from an existing 'latest read' rather than triggering a scan, it needs no API key, and it documents failure modes (never-read site, draft, unnamed site return not found). It stops short of saying how fresh that stored read is or what to do when it is stale.

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?

Labeled lines (When / Instead / Inputs / Returns / Fails) front-load the decision-relevant content and no line is filler. Some phrasing is telegraphic — 'fixes and card, a picture to send the person' — which costs a little readability against otherwise tight structure.

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 two-parameter read tool with no output schema, the description covers return shape, both view modes, auth requirements, and failure cases. Nothing an agent needs in order 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 baseline is 3, but the description earns above it by explaining what `view: agent` actually yields — the whole-site Agent View from the same read, with each AI crawler as robots.txt treats it — which the enum values alone do not convey. `site` adds only the domain-format note already present 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 verb (Gets) and resource (a site's report from its latest read) and enumerates the payload: score, grades, rank, served, fixes with failing pages. The 'Instead' line names three siblings and what each does differently, so an agent can route without opening another 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?

Explicit 'When:' condition ('to tell a person how a site stands') plus an 'Instead:' clause that assigns clickd_brief, clickd_rivals, and clickd_check to their own cases. Both the use case and the exclusions are stated outright.

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=true and openWorldHint=false, the description discloses the auth requirement ('Needs a person's key'), the failure mode ('an account with no claimed site has an empty board'), the default value of `show`, and ordering semantics ('oldest first'). These are exactly the operational facts 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?

Labeled sections (When / Instead / Inputs / Returns / Fails) front-load the essentials with no filler, and every line adds information. The telegraphic fragments ('the next fix and every other by worth') cost a little parseability, keeping it from a 5.

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 compensates by naming the returned fields for both modes (next, todo, slipped, fixed, waiting, note; tasks, note). Combined with the failure case, default, and sibling routing, an agent has everything needed to call 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 enum is already typed, so the baseline would be 3. The description earns above that by explaining what each enum value actually yields: board returns next/every fix by worth/slipped/fixed, queue returns tasks oldest-first — meaning the schema does not convey.

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 ('Gets the person's work across all their sites') and enumerates the two content modes, so an agent can distinguish it from siblings. The domain vocabulary ('by worth', 'what slipped') is slightly opaque on first read, which keeps it just below top marks.

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?

An explicit 'When:' clause names the triggering situations ('when you start work for the person', 'when a reply says tasks are waiting'), and the 'Instead:' clause routes to clickd_brief for single-site fixes and clickd_log_work for finishing a queued task. Both the positive case and the alternatives are stated, not inferred.

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