INITE Directory

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

Annotations already cover safety (readOnly, idempotent, destructive=false, closed world), so the description correctly spends its words elsewhere: the lookup key formats (name before .inite.ai vs own domain), the eligibility precondition ('owners confirmed their facts ... proved their domain'), and the presence of agent-contactable endpoints. It adds genuine context rather than restating hints.

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 one long run-on sentence with heavy parenthetical stacking; the key fact (by slug or domain) is front-loaded, but the Atlas digression and repeated 'INITE' branding inflate it. Most sentences earn their place individually, yet the whole would be tighter as two or three short lines.

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?

An output schema exists, so the description needn't enumerate return fields — yet it does so anyway, which is redundant but not harmful. Nothing an agent needs in order to call it correctly is missing; the only gap is the sibling disambiguation against find_business.

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 both parameters carry examples, so the schema does the heavy lifting. The description restates the slug definition ('the name before .inite.ai') and adds that the two parameters are alternatives, but contributes no format or validation detail beyond 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+resource: retrieves 'one business ... by its INITE slug or its domain', and enumerates what it covers (services, hours, locations, MCP/A2A endpoints). It differentiates itself from the Atlas tools but never distinguishes itself from the sibling find_business, which is the more likely confusion point.

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 exclusionary rule: 'the INITE Atlas is AI tools ... use it, not this, for which AI tool or app to use', plus practical qualifying facts ('Free, no account' and the domain-confirmation requirement). It stops short of telling the agent when to choose this over the sibling find_business.

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 safe-read profile; the description adds genuinely new behavior: ranking by word match plus completeness of confirmed facts, an explicit no-paid-placement guarantee, free with no account, prices quoted exactly as the business confirmed them, and the confirmation/domain-proof gating of the index. That is substantial context beyond the structured fields.

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 every clause carries information (scope, multilingual queries, returned fields, follow-up server, ranking, free access). It is a dense single block with some restatement of the confirmation/domain fact, which costs it a point.

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

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

Given an output schema, five well-documented parameters, and full annotation coverage, the description still supplies everything an agent needs: what comes back per result, how ordering works, and where to go for the rest. Nothing material 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 description coverage is 100%, so the baseline is 3; the description lifts it slightly by clarifying that the query accepts a business type, a service wanted, or a place, in English, Russian, Portuguese or Spanish, and that city/country/language are optional narrowing filters. It does not add format detail the schema lacks, so it stays below maximum.

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 businesses) and pins the scope precisely: businesses whose owners confirmed their own facts at INITE, matched by what they do and where. It also draws the boundary against the Atlas/AI-tool directory, so an agent can distinguish it from the sibling surface without opening schemas.

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

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

Explicitly routes the agent: "use it, not this, for which AI tool or app to use," naming match_tools and atlas_lookup as the alternatives. It also states when the answer is insufficient (hours, full service list, Q&A) and points to the company facts MCP/A2A server for those follow-ups.

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

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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so safety is covered; the description adds what the caller actually receives (URL, Claude Code command, Cursor/VS Code install links, custom-connector step for claude.ai and ChatGPT). It says nothing about side effects or failure modes, but there are none material for a read-only lookup. The return-value detail is partly redundant with the existing output schema.

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 dense paragraph with no breaks, and the front-loaded material is a server catalog rather than the tool's own action. Parenthetical fragments like 'INITE and its signed-in door (your account, Local Start)' are hard to parse and slow down routing. No sentence is outright wasteful, but the structure works against scanning.

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 one optional parameter, full annotations and an output schema, the description covers the remaining burden: when to call it, how `for` selects a single answer, and what the response contains. The only gap is that several enum values are left to inference from the catalog phrasing.

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 `for` enum is documented, so baseline would be 3. The prose adds real value by mapping ambiguous enum members to intent — e.g. 'premium'/'add_tool' under the signed-in Atlas, 'licence'/'your audits' under Visibility, 'businesses that confirmed their own facts' for find_business. Two enum values ('talk', 'find_tools') remain unexplained, keeping it from a 5.

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 the resource (INITE's MCP servers and how to add each to this client) and the outcome (returns URL, install commands, connector steps), so an agent can tell it is a discovery/connection-info tool. The opening is a catalog noun phrase rather than a verb+resource statement, so the actual action only becomes clear in the last sentence. It does differentiate from siblings implicitly by being the routing tool for servers this client cannot reach.

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 it when the person wants something this server does not do; give `for` to get the one server that does it' is an explicit use condition plus routing instruction. It does not name the siblings (inite_book_call, inite_services, etc.) as alternatives to try first, so the exclusion boundary is stated as a condition rather than as a ranked alternative.

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