Conscius

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

Beyond the readOnlyHint and openWorldHint annotations, the description explains fact statuses, trust scores, how to interpret Wikidata records, verification expectations, and what happens when no fact is found. It also describes the effect of min_trust and explain on results. This adds substantial behavioral context that an agent needs to use the results correctly.

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

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

The description is front-loaded with the core purpose and is organized around statuses, trust, and parameter effects. It is necessarily detailed for a tool with several status and trust concepts. Some repetition around verifying low-trust or changing facts makes it slightly denser than ideal, but it remains purposeful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the burden of explaining returned facts, sources, statuses, and trust. It does this well enough for an agent to interpret results and decide whether to verify. It does not describe response ordering or pagination, but those are minor for this lookup 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 100%, so the input schema already documents every parameter, including entity formats, enums, and defaults. The description adds some practical guidance around min_trust and explain, such as filtering by trust and requesting reasons. Given that the schema does most of the parameter documentation, a baseline score of 3 is appropriate.

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

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

The description states a specific verb and resource: look up current facts about a named thing in Conscius, including dates, versions, numbers, prices, roles, and attributes. It clearly distinguishes the operation from generic search by emphasizing checkable facts with statuses and trust. However, it does not explicitly differentiate this tool from sibling tools such as conscius_search or conscius_wanted.

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 clear usage context: use it whenever a task needs a specific, checkable fact, and research as usual if nothing is found. It also explains how to interpret statuses and when to verify values, which is useful operational guidance. It lacks explicit when-not guidance and does not name sibling alternatives for related tasks.

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 the write/safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the description carries the real burden and delivers: it states that one call stores the fact, that submit is the default mode, that check validates without storing, and that supporting_text is used for checking then discarded. It does not describe what a rejected or conflicting claim returns, which is the main remaining behavioral gap.

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

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

It is front-loaded with the purpose, then mechanics, then prohibitions — a sensible order with no filler sentences. It is dense and somewhat long, and the exact-quote refetch instruction could be trimmed, but every sentence carries actionable 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?

For a two-parameter write tool with no output schema, the description covers what gets stored, the validation-only alternative, and source-integrity constraints well. What is missing is any indication of what the call returns on success or on problems — e.g. suggested IDs are only hinted at via the `mode` description, not the main text.

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 schema already documents its nested fields in detail, and the description adds meaning on top by specifying the minimum triple to supply (value, page URL, the exact sentence) and by clarifying the verbatim-quote requirement that gives `supporting_text` its purpose. It does not add anything about `plan`, `origins`, `valid_from`, `paid_source`, or `retrieved_at`, leaving those entirely to 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 opening sentence gives a specific verb and resource — share a verified fact from a public web page, with the stated benefit of saving the next agent a lookup. It ties itself to conscius_lookup's `to_propose` output, which helps situate it among siblings, but it never contrasts it with conscius_search or conscius_wanted, so the differentiation is partial rather than explicit.

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 names the trigger condition precisely ('When a conscius_lookup result includes `to_propose`, fill it in'), the exact content required, and a remediation step when a fetch tool returned a summary instead of the page's own words. It also lists four explicit exclusions (private individuals, login-gated pages, private files, unsourced memory) and explains the submit-vs-check choice, so both when-to-use and when-not-to-use 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?

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds real substance on top: results carry IDs, top facts, a per-fact status, and sources. With no output schema, this return-shape and provenance disclosure is genuinely useful. It stops short of explaining what the status values mean or how results are ranked, which keeps it off a 5.

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

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

Four short sentences, front-loaded with the purpose before the usage condition and the return shape. Every sentence contributes a distinct piece of information with 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 a three-parameter search tool with no output schema, the description covers purpose, trigger, return shape, and next step, which is close to what an agent needs. The remaining gap is the undocumented response_format enum and the absence of any guidance on query phrasing beyond the schema example.

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 67%, with query and limit well documented in the schema itself. The description adds no parameter-level meaning beyond that, and response_format is an enum with no explanation of what concise versus detailed actually changes in the response. Baseline 3 is appropriate since the schema carries most of the load.

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

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

States a specific verb and resource ("Find facts other agents have already verified") and immediately scopes the corpus as pre-verified agent-contributed facts, which separates it from generic search. It also names the sibling conscius_lookup for the follow-up step, so an agent can distinguish the two without inspecting either schema.

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

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

Gives an explicit triggering condition — you need a specific fact (date, version, number, price, role holder) but aren't sure of the exact name of the thing — and explicitly routes to conscius_lookup for more detail. Both when-to-use and the alternative are stated rather than 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 only declare readOnlyHint and openWorldHint=false, so the description carries the burden of explaining the payload: each item is a thing-plus-property several agents missed, with an ask count, and needs_confirmation means one source exists and an independent second is needed. That is meaningful semantics beyond the annotations, though pagination beyond limit and total counts are not addressed.

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

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

Front-loaded with purpose and filtering before the fill workflow, and each sentence is substantive. It is somewhat long for a list tool — the sourcing rules (public page, open, send via conscius_propose) arguably belong with conscius_propose — but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description must explain return shape, and it does: item structure, ask counts, and needs_confirmation. Combined with the filtering hints and source restrictions, an agent has everything needed to call it correctly and interpret results.

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 all three parameters are documented there, so the baseline is 3. The description adds only the routing hint 'narrow it with entity or topic', which is useful but thin relative to what the schema already says.

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 — see the facts other agents needed and Conscius didn't have, i.e. the wanted list — and immediately frames it against ordinary task work and against conscius_propose for filling. An agent can tell this apart from conscius_lookup/search 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-to-use (user asks to help fill Conscius, or contribution work) and when-not-to-use (ordinary tasks), plus the concrete alternative for the follow-up action (conscius_propose). It also lists prohibited sources: memory, pages behind a login, private individuals.

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