Antevo Trademark

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

Annotations already declare read-only, idempotent, open-world, and non-destructive behavior, but the description adds important caveats: not_checked semantics, none_found not meaning clearance, recent filings possibly missing, and unregistered domains being takeable. This is substantial behavioral disclosure beyond the annotations.

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 purpose is front-loaded, and the remaining details on ranking, parameter effects, return shape, and caveats are dense but necessary for a tool with no output schema. No obvious filler is present.

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 must explain return values, and it does: per-name trademark verdicts, near-mark counts, closest marks, company results, domain status, and not_checked behavior. It is complete enough for an agent to call and interpret the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry parameter meaning. It defines the names limit, the effect of classes as Nice class numbers, and countries with examples and their effect on company registers and domains, covering all three parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Screens a shortlist of up to 15 candidate names in one call') and enumerates the three checks: trademarks, companies, and domains. It is clear, but it does not explicitly distinguish this from sibling tools such as screen_mark.

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 clear context for shortlist screening, notes that no account is needed, and explains how optional classes and countries alter coverage. However, it does not state when to prefer this tool over screen_mark or other alternatives.

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, openWorld, and non-destructive behavior, so the safety profile is covered. The description adds that PermID corporate identity and CC BY 4.0 credit are included, which is useful output context but not deeper behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loads the scope statement before the attribution note. It is appropriately sized, though the first sentence is cryptic enough that its brevity sacrifices clarity.

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 and a single undocumented parameter, the description is too sparse to tell an agent what the "book" contains, how results are structured, or what the name parameter requires. It supplies a partial data-provenance note but leaves core invocation and return expectations incomplete.

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 sole parameter "name" has no schema description (0% coverage) and the description does not explain what the name represents, its expected format, or whether it identifies a holder or company. The phrase "A holder's whole book" only loosely implies the name is a holder identifier.

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 largely restates the title ("A holder's WHOLE book") without a clear verb or resource explanation. It adds scope ("across every office. Founder and up") and mentions PermID attribution, but an agent still cannot tell precisely what the tool returns or how it differs from holder_read.

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 explicit guidance is given on when to use this tool versus alternatives such as holder_read. The phrase "WHOLE book" implies comprehensiveness but does not state conditions, exclusions, or sibling comparisons.

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 idempotentHint=true, destructiveHint=false and readOnlyHint=false, so the safety profile is largely covered. The description adds genuinely useful context beyond that: the action is reversible and the hit moves to the Cleared list, where it stops being surfaced. Auth requirements and rate limits are not mentioned.

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 short paragraphs, front-loaded with the effect ('Clear one hit as not-a-threat') before the parameter sourcing rules. The final sentence overlaps somewhat with the opening but adds a concrete example of what a cleared hit looks like.

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 mutation tool with no output schema, the description covers the essentials: the state change, its reversibility, and how to source the required identifiers. The main gaps are the two optional parameters and any permission requirements.

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 0%, so the description must compensate. It does explain that jurisdiction and app_no must match 'exactly as they appear on a conflict in the user's conflict list,' which is real value, but it says nothing about the optional applicant and mark_text parameters, leaving half the parameters undocumented.

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: 'Clear one hit as not-a-threat,' and contrasts it with the conflict list it draws from. It is clearly distinct from listing siblings like my_conflicts or screening tools like screen_mark, though it never names a sibling 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?

It implies the usage context (a hit appearing on the user's conflict list, such as an unrelated business or the user's own filing) but never states when to use this versus alternatives, nor any exclusion or prerequisite. Guidance is inferable rather than 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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds a real access constraint ('Studio and up'), which is genuine auth/tier context, but leaves 'lately' undefined and the tier term unexplained, so the recency window remains unknown.

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 short fragments, front-loaded with the core behavior and zero filler. The second fragment is efficient but too terse to be self-explanatory.

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 parameters, no output schema and rich annotations, the description only needs to convey scope and constraints. It conveys scope but leaves two consequential gaps: what 'lately' means (time window) and what 'Studio and up' gates, both of which affect whether the agent can rely on 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?

The tool takes zero parameters, so there is no parameter semantics to document and the baseline of 4 applies. The description correctly implies the call is fully implicit in the authenticated user's follow graph.

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 names a specific resource and scope: a feed of recent filings from filers the user follows, which no sibling tool provides. The trailing qualifier 'Studio and up' is unexplained jargon and muddies rather than sharpens the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no when-to-use guidance and does not contrast with plausible alternatives such as filing_landscape or my_watches. An agent must guess whether this is a personalized social feed or a search surface.

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 read-only/idempotent/open-world, and the description adds substantive behavior beyond them: 'Signed-in' auth requirement, and a prominent data-integrity caveat that counts reflect the mirror, not the office, with per-office `coverage` and `do_not_quote` fields flagging unreliable offices. This is exactly the extra context an agent needs before quoting numbers.

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 invocation, then the caveat — a logical order with no filler. The mirror/coverage warning is somewhat dense, but every 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 still sketches the return shape (volume by month, busiest filers) and names output fields (`coverage`, `do_not_quote`) that govern interpretation. Combined with the auth note and caveat, an agent has everything needed to call and correctly read this tool.

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 0%, so the description must carry the load, and it does: examples for nice_class (9, 42, 36…), 'office code' values for jurisdiction ('EM','US','GB','CH'), and the meaning of months as a window. It does not explain the empty-string jurisdiction default or reconcile that the schema calls the field 'jurisdiction' while the prose calls it an office code.

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?

Names a specific verb and resource: 'Filing activity in a Nice class — volume by month and the busiest filers.' An agent can tell this is a class-level aggregate. It stops short of explicitly distinguishing itself from the close sibling filer_activity, so a 5 is not earned.

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?

Frames the intent with 'Answers "how crowded is my space" and "who keeps filing near me"' and gives concrete invocation guidance (class, optional office code, window in months). It provides clear context but names no explicit alternative or when-not condition, so no 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 the safety profile (idempotentHint=true, destructiveHint=false, openWorldHint=true), so the bar is lower. The description adds useful plan-tier context ('Studio and up') and implies a persistent ongoing subscription rather than a one-off action, but says nothing about failure modes for lower tiers or how a follow is later removed.

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 short sentences, front-loaded with the core action and scope, with no filler. The 'Studio and up.' fragment is terse but functional.

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 one-parameter mutation tool with no output schema, the description covers purpose, tier requirement, and the behavioral distinction from watching a name. It omits the filer identifier format and any lifecycle detail (how to stop following), which an agent would still need.

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 0% and the single 'filer' parameter is completely undocumented in the schema, so the description carries the full burden. 'Follow an adversary' clarifies that the value is an entity/person rather than a filing, but never specifies the expected format (name, CIK, or internal ID), leaving the agent guessing what to pass.

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 ('Follow an adversary — every filing they make, anywhere'), which is clearly distinct from one-shot lookups like filer_activity. It also contrasts itself against the 'watching a name' concept, though it does not name the sibling tool (e.g. watch_mark) 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?

Gives a clear selection rationale — use this to catch what a filer does NEXT rather than tracking a name — plus an eligibility prerequisite ('Studio and up'). It stops short of naming the alternative tool or stating when-not to use it.

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 and open-world, so the safety profile is covered. The description adds value beyond that by noting the call is free and by explaining that `remaining` = `monthly_left` (resets monthly) + `topup_balance` (never expires), which is genuine behavioral/return semantics not available in any structured field.

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 short, front-loaded paragraphs: the first says what the tool is and that it's free, the second decodes the return fields. No filler sentences, and the most decision-relevant line (what you get) comes first.

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 parameters and no output schema, the description carries the return-value burden and does so adequately, naming `remaining`, `monthly_left`, `topup_balance`, and `prices` with their meanings. Nothing an agent needs to call or interpret this tool is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the 4 baseline applies. The description introduces no parameter concepts, and none are needed.

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 exactly what the tool returns: the user's spendable credits and the per-tool credit price of paid tools. No sibling tool covers billing/credits, so the agent can select it unambiguously from this sentence alone.

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?

'Free to call' gives a useful cost/economy signal and implies it can be called liberally, e.g. before invoking a paid tool. However, there is no explicit statement of when to use it versus alternatives, nor any exclusion or trigger condition — usage is only 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 cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description adds real substance beyond them: findings are computed from the holder's whole register book, evidence is returned per finding, no legal conclusions are drawn, and PermID corporate identity carries a CC BY 4.0 attribution obligation. It does not describe result shape or any rate/latency behaviour.

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 opening sentence front-loads the purpose well, but the middle sentence is dense with framing rhetoric ('the leverage that gives counsel', 'spray across unrelated classes') that costs tokens without adding callable detail. Three sentences is reasonable in length, but signal density is mixed.

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 does a fair job of telling the agent what comes back (evidence behind each finding, attribution credit). It is nevertheless incomplete on the input side — nothing about the 'name' argument — and gives no sense of result size or how findings are structured.

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 0% for the single required parameter 'name', and the description does not compensate: it never says whether the value is a legal entity name, a trading name, an exact or fuzzy match, or how ambiguous names are handled. The only hint is the recurring word 'holder'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource (a trademark holder) and states what the read yields: identity, filing behaviour, lapse rate, class clustering. It is clearly a profile/analysis read rather than a list or a search. It never names a sibling (e.g. company_file or run_investigation) to force a routing decision, so it stops short of 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?

The framing 'the read on an adversary' and 'Free' imply the when: adversarial due-diligence work where cost matters, versus the paid investigation siblings. Usage is only implied, with no explicit when-not and no alternative tool named, so it is adequate but not directive.

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, destructiveHint=false and openWorldHint, so the safety profile is fully covered. The description adds only the words 'currently' and 'watches' — it says nothing about result volume, ordering, recency window, or whether 'near' includes fuzzy/phonetic matches, which is exactly the kind of context an annotation cannot supply.

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 with no padding or repetition of the title, which is appropriate for a no-argument query tool. It is efficient, though the brevity shades into under-specification rather than genuine conciseness.

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 zero-param, no-output-schema tool the description is the only source of semantics, and the one ambiguous term ('near') is left unexplained. The agent cannot predict what constitutes a match or how results are scoped, which is the central unknown for this tool.

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 zero parameters, and the schema has 100% description coverage, so there is nothing for the description to compensate for. Baseline of 4 applies; the description cannot add parameter meaning that does not exist.

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 phrase 'Everything currently near the names this user watches' gestures at retrieving conflicts for watched marks, but the operative word 'near' is never defined (similarity? phonetic? class overlap?) and there is no verb telling the agent what operation this is. It does scope the result to the user's watches, which separates it somewhat from sibling tools like filing_landscape, but it does not distinguish itself from my_watches or dismiss_conflict.

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 when-to-use guidance, no stated prerequisite (e.g., that watches must exist), and no reference to adjacent siblings such as my_watches (manage watches) or dismiss_conflict (act on a conflict returned here). The agent must infer that this is the read-side counterpart to dismiss_conflict entirely on its own.

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 establish readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real value beyond that by defining the semantics of each `kind` value, including that `window_pending` means nothing is running yet and `window_closed` means the route is now cancellation — crucial context for interpreting results.

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 what the tool returns, followed by a compact enumerated taxonomy. The backtick formatting makes the state machine scannable; no filler text.

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 burden of explaining returns, and it does cover only the `kind` field — it says nothing about other fields on a deadline (dates, marks, parties) or ordering/volume of results. Adequate for the taxonomy, but incomplete as a stand-in for a missing output schema.

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 zero parameters, so per the rubric the baseline is 4. The description's discussion of `kind` applies to returned data rather than inputs, but nothing about input semantics is missing.

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 and scope: renewals and closing opposition windows belonging to 'this user'. It is clear what the tool surfaces, but it never names or contrasts with the adjacent sibling `opposition_window`, so an agent cannot fully disambiguate the two from the description alone.

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 statement of when to call this versus `opposition_window`, `my_watches`, or `my_conflicts`. The `kind` taxonomy explains what results mean, not when the tool should be selected, so usage is left entirely 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 already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is fully covered. The only added context is that results are scoped to 'this user'; nothing is said about whether the list is empty-able, ordered, or paginated.

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?

It is a single short sentence with no padding, which is good, but it is under-specified rather than deliberately minimal — the same length could have carried a verb and a pointer to watch_mark.

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 zero-parameter read with annotations covering safety, the definition is nearly complete; however, with no output schema, the description never says what the returned 'names' look like (plain strings vs. watch records with mark metadata), which leaves a real gap.

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 zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly implies no input is needed because the user scope is implicit.

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 restates the title almost verbatim ('The names this user is watching'), giving the resource and user scope but no explicit verb (list/retrieve) and no differentiation from the sibling watch_mark, which is the obvious counterpart for adding a watch.

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 indication of when to call this versus siblings such as watch_mark (add a watch) or my_conflicts/my_deadlines. The agent must infer from the name alone that this is a retrieval tool.

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 (readOnly, idempotent, non-destructive, openWorld). The description adds real behavioral value on top: the shape of the result (twenty registers, each carrying the source provision) and the semantic trap about pre- vs post-registration windows. It does not disclose response format details or fallback behavior for unknown offices.

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 answer, then the return shape, then the trap, then accepted input formats. Every sentence carries information, though the 'trap' paragraph is somewhat discursive relative to the one-parameter lookup it describes.

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 correctly describes what comes back (twenty registers plus the governing provision) and what the tool is for. Minor gap: it does not state units or granularity of the window (days vs months) or what happens for an unsupported office.

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 0%, so the description carries the full burden for the single 'office' parameter, and it does: it accepts a country name, an office name, or a two-letter code, with concrete examples ('japan', 'JP', 'EU'). This is exactly the compensating detail the schema lacks.

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 (opposition window per trademark office) with the two dimensions it returns — duration and trigger point. No sibling tool covers this, so the agent can route to it unambiguously.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description frames the use case explicitly: determining opposition deadlines and avoiding the mistake of applying one office's rule to another. It lists the exception offices (Switzerland, Germany, Japan, Sweden) that behave differently, which is effectively usage guidance. It does not name a sibling alternative or a when-not-to-use condition, so it stops short of a 5.

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

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

Goes well beyond the annotations: it discloses the cost model, that failed runs are free, and that repeat calls for the same holder inside 30 minutes are served from cache with reused: true. It reconciles the destructiveHint=true / readOnlyHint=false annotations by naming the resource actually consumed (one credit) and closes with a candid 'check, not register fact' caveat about AI-authored sourcing.

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 the tool produces before covering cost, caching, and the reliability caveat, and each sentence does work. The middle credit sentence is dense with parenthetical details, but nothing is padding.

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 sketches the dossier's contents, cost, auth prerequisite, and cache behavior, which is most of what an agent needs. Left unstated are error/retry behavior, what happens with ambiguous or unknown holders, and whether the dossier persists server-side (relevant given the sibling holder_read).

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?

One parameter at 0% schema coverage, so the description must carry it. It implies 'name' means the trademark holder being researched and that matching is holder-scoped ('same holder'), but gives no guidance on accepted forms (legal entity vs. brand name, aliases, partial matches) or how duplicates are resolved.

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 ('Research a trademark holder on the open web') and enumerates exactly what the returned dossier contains (identity type, notable activity/disputes, red flags). That output specificity implicitly separates it from the read-style sibling holder_read, but no sibling is ever named, so the differentiation is inferred 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?

Gives clear call context: it requires a signed-in session and it burns a credit, with the charge order (included before purchased) spelled out. It does not, however, say when a holder should be researched here versus simply read via holder_read, nor warn about ambiguous holder names.

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/openWorld annotations, the description discloses the result shape (up to 25 marks, similarity tier, filing registers) and an important data-freshness trait: EU marks are live from EUIPO but other registers come from a refreshed copy where recent filings can be missing. It also sets expectations that results are a screen rather than clearance.

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 short sentences with the scope first, the return content second, and the caveat last. Every sentence earns its place and nothing is padded.

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 return semantics (what the marks include, how many, and which registers) plus the freshness limitation. For a one-parameter read-only screen, nothing an agent needs in order to call and interpret it 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 0% and the single `mark` parameter has no schema description, so the description must carry the meaning. It does by establishing that exactly one brand name is screened (not a batch), though it says nothing about expected format or normalization of the name.

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 ("Screens one brand name against trademark registers") and pins the scope to a single name rather than a list. It is clear on its own but never names a sibling such as check_names or run_investigation, so an agent must infer how it differs from the other screening tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"No account needed" and "It is a screen, not clearance" give a clear context and a hard usage boundary, which is exactly the kind of framing an agent needs before presenting results to a user. However, no alternative tool is named and no explicit when-not conditions beyond the clearance caveat are given.

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 and openWorld; the description adds context beyond that: no account required, no register queried, and an explicit output shape (classes plus per-class reasoning plus a closing caveat about what the report does not mean). It does not cover error cases or how many classes typically come back, keeping it below 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?

The purpose and boundary are front-loaded, which is good, but the middle paragraph on the 45-class numbering (class 9 vs 42 vs 35) is educational filler that does not change how the agent calls the tool. Roughly a third of the text could be cut without losing invocation-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?

There is no output schema, and the description fills that gap by describing what is returned (classes with reasoning and a caveat). Combined with the annotations' safety profile, 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 0% and the single 'description' parameter is undocumented in the schema, so the description must compensate. It does: "Takes a description of the business" tells the agent exactly what to supply, though it gives no guidance on length, detail, or whether goods/services must be enumerated.

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 (maps/suggests) and resource (Nice classes) and explicitly disclaims what it is not: "no register is searched", which separates it from check_names and screen_mark. The parenthetical contrast of "is my name taken" vs "taken in WHAT" makes the tool's job unmistakable.

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 clear context for use (a business needs to know which classes to file in) and a negative boundary (it does not search a register, so it is not a name availability check). It never names the sibling to call instead for name checks, so it stops short of explicit routing.

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 idempotent, non-destructive, and closed-world behavior. The description adds the observable effect (conflicts on new filings) and class scoping, but leaves 'near it' undefined and does not mention permissions or what the watch record looks like.

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 compact sentences with the core action front-loaded and the optional parameter behavior following. No wasted text.

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 simple mutation tool with annotations covering safety, the description is mostly complete. However, it does not clarify the 'near it' matching concept or what a caller should expect after the watch is created.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It does: 'brand name' implies the required mark, and classes are explained with format example ('9,42') plus the blank-every-class default. Minor gaps remain around mark format constraints.

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 ('Start watching') and resource ('brand name'), and explains the effect (new filings near it show up as conflicts). It is clear but does not explicitly differentiate from siblings such as screen_mark or my_watches.

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?

Implies when to use it by saying 'Start watching a brand name', but gives no explicit when-not guidance or alternatives like screen_mark for one-off checks. The optional classes behavior is defined, but comparison guidance is absent.

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