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

Annotations already cover safety (readOnly, idempotent, closed-world), so the description's job is to add context — and it does, by disclosing that the response is metadata including required Populi roles and a docs link, which tells the agent this is a documentation lookup rather than a data fetch. It doesn't describe size/format of the reference payload, but with readOnly+idempotent declared that gap is minor.

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 sentence that front-loads the payload contents and closes with the two ways to invoke it. No filler, nothing repeated from the schema verbatim.

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, but the description enumerates the return contents (placeholders, typed params, expandable properties, filters, roles, docs link), so the agent knows what to expect. All three optional parameters are covered and the read-only nature is declared via annotations.

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 genuine meaning: it distinguishes the id-based lookup from the combined method+path lookup and indicates the id comes from populi_search_api. That relationship (id alone vs. method and path together) is not stated 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+resource ('Full reference for one route') and enumerates exactly what the reference contains: placeholders, parameters with types, expandable properties, filter conditions, roles, and a docs link. This makes it unambiguous against siblings like populi_get (fetch data) and populi_search_api (find routes) without needing 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?

'Pass a route id from populi_search_api, or a concrete method and path' gives clear entry conditions and points at the sibling that produces valid ids. It stops short of any exclusion (e.g. 'use populi_get instead if you already know the route and want data'), so it is clear context without explicit when-not guidance.

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 the never-overwrite naming convention (-1, -2 suffixes), the saved-path-plus-preview return shape, and the all_pages/max_records loop behavior. Nothing contradicts annotations: readOnlyHint=false correctly reflects local file writes, and destructiveHint=false matches the never-overwrite guarantee.

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 sentences, front-loaded with the core behavior, then use cases, then the non-obvious file-naming and return behavior. No filler or restatement of the tool name.

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?

Ten parameters with nested objects and no output schema, yet the description covers purpose, when-to-use, the pagination escape hatch, file collision behavior, and what comes back (path + preview). 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 baseline is 3. The description earns above-baseline credit by explaining collision handling for save_as and the purpose of all_pages, details the schema does not state, though it does not clarify page/limit/expand semantics 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 and resource (GET a Populi route) plus the key divergence — result goes to a file instead of the conversation. Explicitly differentiates from the sibling populi_get by saying it takes the same arguments but saves output, so an agent can pick between them 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?

Names concrete when-to-use cases: file-returning routes (PDF/XLS/CSV, transcripts, Data Slicer, backups, images) and oversized lists/exports where all_pages should be used. The 'instead of returning it' phrasing implicitly routes non-file, small-payload reads to populi_get.

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, so the safety profile is covered; the description then adds match semantics, the constraint that at least one criterion is required, and what the response contains (people list plus report_data with primary email/phone). Useful value beyond structured fields, though result ordering and pagination behavior 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?

Four tight sentences, front-loaded with the core action and match semantics, then the return shape, then the pointer for deeper data. No redundant 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?

With no output schema, the description usefully summarizes return values (ids, names, status, report_data block) and explains the escalation path for full contact records. Nearly complete; ordering/truncation behavior of results is the only noticeable 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?

Schema coverage is 100%, so baseline would be 3; the description goes further by stating the exact-vs-contains matching behavior per field and adding an invocation rule ('Needs at least one criterion') that no schema constraint expresses, since required is empty. limit is left to the schema, which documents it fully.

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 ('Look up people') plus the exact searchable criteria (email, first/last name). This is clearly a specialized people-search tool, distinguishable from generic siblings like populi_get or populi_search_api 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?

Gives the precondition 'Needs at least one criterion' and the matching semantics (email exact, names contains), and points to the alternative route ('/people/{id}' with expand) for full contact records. No explicit when-not-to-use, but the routing to the alternative covers the main decision.

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 read-only/idempotent/open-world, and the description adds context they cannot: ~50 requests/min rate limit, 200-record default page size, and the failure mode where all_pages stops mid-run but returns fetched pages plus a next_page to resume. That is exactly the operational behavior an agent needs before invoking.

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 and path shape, then pagination, filtering, rate limits, and the sibling escape hatch in a logical order. The inline filter JSON literal is dense but earns its place as a copyable template; slightly heavy overall.

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 open-world passthrough with no output schema, it covers paths, pagination, filtering, expansion, rate limits, partial-failure recovery, and the file-route alternative. The only thin spot is describing the single-object (non-list) response shape.

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: a concrete filter object example, the note that expand names must come from populi_describe_api, and how page/limit/all_pages interact. It stops short of explaining params/max_chars/max_records beyond the schema text.

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 ('GET any Populi API v2 route') plus the read-only constraint and a concrete path shape with examples. It also distinguishes itself from siblings by naming populi_describe_api for expand names and populi_download for file-returning routes.

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 (generic /api2 route reads), explicit when-not (PDF/XLS exports, transcripts, Data Slicer, file downloads → populi_download), and an efficiency rule ('prefer one filtered call over many unfiltered ones'). 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 already declare readOnly, idempotent and closed-world, so safety is covered. The description adds genuinely useful context the annotations cannot: the size of the catalog and the exact return shape ('route ids with method and path'). It does not mention the default/maximum result limit or truncation behavior, which keeps it short of 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?

Three short sentences, front-loaded with the resource and scale, then the return shape, then the routing instruction. Nothing is redundant and every sentence carries information an agent needs.

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 read-only search with three simple parameters and no output schema, the description supplies everything needed: what is searched, how large the corpus is, what comes back, and which tool to call next. No material gap remains.

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 query, method and limit are all documented in structured fields. The description reinforces the query parameter with example keywords, but says nothing about the method filter or the limit semantics, so it adds only marginal value over 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 and resource ('Search the Populi API v2 route catalog') with concrete scale (697 routes / 180 models) and example keywords. It also distinguishes itself from the sibling populi_describe_api by naming that tool as the next step, so an agent can route between them 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?

'Use this first to find the right route, then populi_describe_api for its parameters' gives an explicit ordering and names the alternative tool. The one gap is that it doesn't say what to do when you already have an exact route id, though the schema covers that case.

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/openWorldHint, and the description stays consistent while adding real context: `verify` triggers one live external request, and write capability may or may not be enabled. It stops short of saying what a failed verification looks like or what latency/error surface to expect.

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, zero filler, with the primary capability front-loaded and the optional parameter behavior trailing. Nothing is repeated from the schema verbatim.

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 the necessary work by naming the three facts returned. It is slightly thin on what differs in the output when `verify` is true (e.g., an auth error vs. a status field), but an agent has enough 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 baseline is 3; the description earns an extra point by clarifying that `verify` costs exactly one live request against the API, which tells the agent this is a non-trivial network round-trip rather than a local flag check.

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 ('Shows') and enumerates exactly what is reported: target instance, sandbox-vs-production key, and write enablement. The diagnostic nature distinguishes it cleanly from the data-access siblings (populi_get, populi_search_api, populi_find_people), none of which report server configuration.

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 second sentence explains what setting `verify` does, which implies the usage context (credential sanity check), but the description never says when to call this tool versus alternatives, nor when to leave `verify` off. Usage is inferable rather than stated.

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