Agent Demand Registry

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real value on top by disclosing what comes back — per-category request counts, median stated price, and reviewed vs. unreviewed requests — which matters because no output schema exists. It stops short of describing ordering, volume, or pagination behavior.

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 tight sentences with no filler; the primary purpose and the returned data are front-loaded, and the secondary capability (reviewed requests available for endorsement) follows. Nothing restates the title or wastes words.

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

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

For a single-optional-enum-parameter read tool with no output schema, the description covers what the agent needs: what it returns and that some entries are endorsable. Minor gaps remain around result ordering, breadth of results, and any implicit link to endorse_demand as the next step.

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?

With one optional parameter at 100% schema coverage and a full enum of categories, the schema already carries the semantics. The phrase "per category" reinforces that results are grouped by category and that the parameter narrows scope, but adds no detail beyond that 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?

The description gives a specific verb-and-resource pairing ("See which datasets and services agents are asking for") and names the returned fields (request counts, median stated price). It distinguishes browse-style reading from write-oriented siblings implicitly by describing a listing, but never names endorse_demand, find_data_source, or register_demand to make the boundary 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?

Usage is implied rather than stated: the agent can infer this is the read surface for demand data and that endorsing is a follow-on action ("reviewed requests you can endorse"), but there is no explicit guidance on when to pick this over find_data_source or register_demand, and no conditions or prerequisites 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 the mutation profile (readOnlyHint false, idempotentHint true, destructiveHint false), so the description's job is to add context. It clarifies that endorsement is additive rather than a new request and that the price is optional, but says nothing about what happens on re-endorsement, whether an endorsement can be withdrawn, or whether it affects the demand's existing price.

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 action and immediately followed by the sibling routing rule. No redundant 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?

The core action and the sibling choice are covered, and annotations carry the safety profile, but for a mutation tool with five parameters, no output schema, and only 20% schema coverage, the missing meaning for currency and expected_monthly_units leaves real gaps an agent must guess at.

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 only 20%, and the description compensates only partially by hinting at "your own price" (max_price/price_unit). currency and expected_monthly_units are left with no explanation anywhere, including what unit basis or magnitude the agent should supply.

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?

"Add your support (and optionally your own price) to an existing request" names the verb (endorse) and the exact resource (an existing demand), and the reference to browse_demand makes it distinct from register_demand without needing the schemas 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?

"Prefer this over registering a duplicate" gives a clear routing rule against the register_demand sibling, and "existing request from browse_demand" tells the agent where the demand_id comes from. There is no explicit when-not case (e.g., what to do if no matching demand exists), 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description earns credit for disclosing that results are 'curated third-party sources' (i.e., a fixed catalogue rather than a live crawl) and for prescribing sequencing relative to scraping. It does not say what happens when nothing matches or how many candidates come back.

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 in the first clause, then scope, then the workflow instruction — every sentence earns its place. The domain enumeration is slightly long and partially redundant with the enum, which keeps it just short of 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?

For a two-parameter discovery tool with annotations and no output schema, the definition covers purpose, input intent, output nature, and sequencing advice. The remaining gaps — empty-result behavior and the role of the optional category — are modest but real.

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 50%: 'need' is well documented in the schema, while 'category' is only an enum with no description. The description's domain list loosely mirrors the enum values but never tells the agent what 'category' does, whether it is an optional filter, or how it interacts with 'need' — so it does not compensate for the coverage gap.

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 where to get a dataset or data API') and immediately bounds the scope with a domain list. The second sentence clarifies the output nature (curated third-party sources) rather than live data pulls, which an agent could not infer from the name 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?

'Call this before scraping or guessing' gives a clear trigger condition and effectively positions the tool ahead of ad-hoc web fetching or hallucinated sources. It stops short of stating when-not to use it or naming a concrete alternative, so it is clear context without full exclusions.

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 this is a non-destructive, idempotent write with no open-world side effects. The description adds genuinely new behavioral facts: registering is free and takes no payment, and personal data must be excluded — both material to an agent deciding whether to call it. It stops short of saying what happens after submission (who sees the demand, whether a match or contact follows).

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 clauses, front-loaded with the action and resource, and every clause earns its spot: what to record, the monetary semantics, and the privacy constraint. No filler or repetition of schema content.

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

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

For a 20-parameter submission tool with no output schema, the description covers the intent and two key constraints but omits the downstream lifecycle — what a registered demand is used for, whether it is published to suppliers, and whether the agent will be matched or contacted. That omission leaves the agent unable to explain consequences to its principal.

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 80%, so the schema already carries most parameter meaning and the baseline of 3 applies. The description restates the concept of max_price but adds no syntax or format guidance, and with 20 parameters several enum fields (urgency, currency, delivery, freshness, payment_rails, principal_type) remain undocumented in both description and schema.

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

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

The description gives a specific verb ('Record') and resource ('demand') and enumerates the kinds of things that can be registered (dataset, API, MCP tool, service), plus the key attribute (max price). It does not explicitly distinguish itself from siblings like browse_demand or endorse_demand, so an agent must infer the distinction from the names 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; no payment is taken' signals this is a non-transactional registration, which implies it is the entry point rather than a discovery or endorsement action, but no explicit when-to-use or when-not-to-use guidance is given. None of the sibling tools (browse_demand, endorse_demand, find_data_source) are named as alternatives or complements.

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