TheAIMeters

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's added value is its disclosure that data is returned as stored without recalculation and that a missing meter yields a tool error. That is meaningful beyond the annotations, though nothing is said about payload size or caching 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?

Three tight sentences, front-loaded with the action and key, followed by usage conditions and return behavior. No filler or repetition.

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 return values need not be documented, yet the description still covers the notable return semantics (raw stored data) and the failure mode. Nothing needed to invoke this single-parameter tool correctly 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 100%, so the baseline is 3, but the description adds real semantic constraints beyond the regex: the slug is exact and comes from list_meters/search_meters, and a UUID will not work. The schema's pattern only implies that prohibition.

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 one meter'), names the exact lookup key ('by its exact slug from list_meters'), and explicitly distinguishes itself from text search, which cleanly separates it from search_meters and list_meters.

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 when ('Use this when the slug is known') and a when-not ('this is not a text search'), which routes the agent to search_meters when no exact slug is available. Provenance of the slug is also specified.

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/non-destructive, but the description adds two non-obvious traits: content is returned backend-authored 'as-is' (so the agent should not expect transformation or normalization), and an unknown meter slug produces a tool error rather than an empty result.

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 dense sentences, each doing distinct work: purpose, mode selection, and error/return behavior. Front-loaded with the core purpose and no filler, though the phrasing is packed enough that it borders on terse.

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 return-value shape need not be explained. For a single optional-parameter read tool, the description covers both modes, the parametrization rule, and the failure case — only the relationship to get_sources/get_meter is left implicit.

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 slug pattern is documented, so the baseline is 3. The description goes beyond the schema by explaining what omitting the parameter means and that the slug must be exact, which is behavioral semantics the schema alone doesn't convey.

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 first sentence names a specific verb and resource ('Explain how TheAIMeters indicators are produced'), and the next two sentences clarify the two operating modes (general vs. per-meter). It does not explicitly distinguish itself from get_sources, which could also surface 'structured sources,' leaving partial sibling ambiguity.

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 conditional rule: omit slug for the general methodology and mappings, supply an exact meter slug for calculation-level detail. It also warns that an unknown slug is a tool error. It stops short of naming when to prefer get_sources or get_meter instead.

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 a genuine boundary ("Does not fetch the referenced external websites") and describes the shape of the returned catalog. It stops short of rich behavioral detail, but for a zero-arg read tool that is a minor 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?

Three short sentences, each doing distinct work: purpose, routing to the alternative, and scope exclusion. Nothing is redundant and the core purpose is front-loaded.

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?

A zero-parameter read-only listing tool with an output schema and full annotation coverage needs only purpose, an alternative route, and scope boundaries, all of which are present. No information an agent needs to call it correctly 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 no parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The mention of IDs/names/URLs/categories describes output fields rather than adding parameter meaning.

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 ("List the complete TheAIMeters source catalog") and enumerates the returned fields (stable IDs, names, URLs, categories). It is clearly distinguishable from siblings like get_methodology and list_meters.

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 frames the use case ("overview of references") and names the alternative plus the selecting condition ("For sources supporting one specific meter, use get_methodology with its slug"). It also states a scope exclusion, so 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 readOnlyHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds a useful behavioral detail beyond annotations: values are returned without recalculation, which affects result semantics.

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 zero waste. It states the action, source, and a key behavioral constraint efficiently.

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 no-parameter list tool with rich annotations and an output schema, the description is largely complete. The one gap is that it doesn't help the agent select between this and search_meters, but the core behavior is sufficiently specified.

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 no parameters, so there is no parameter semantics to describe. The schema is empty and coverage is 100%; baseline for zero parameters is 4.

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 ('List all meters') and adds the scope 'as returned by the TheAIMeters API'. It distinguishes from siblings implicitly by saying 'all' and 'without recalculating', but never names search_meters or get_meter as alternatives, so sibling differentiation is incomplete.

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 explicit guidance on when to use this tool versus search_meters or get_meter. The only implied usage is 'list all meters', leaving the agent to infer that this is for unfiltered retrieval.

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 past the safety annotations by disclosing the matching algorithm (literal, case-insensitive substring), the searched fields, the result ordering, that it is not semantic search, and that no matches yields an empty meters array. With readOnlyHint/idempotentHint already covering safety, this is meaningful added context.

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, each carrying distinct information (purpose, matching behavior, negative case, alternative). Front-loaded with the selection condition before the mechanics.

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 return-shape detail is optional, yet the description still adds the empty-result behavior. For a one-parameter read tool with full schema coverage and annotations, nothing an agent needs to call it correctly 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 100% and the schema already documents the single query parameter including literal percent/underscore handling, so the baseline is 3. The description adds genuine semantics beyond the schema: literal case-insensitive substring matching across slug, label, group and sourceNote, plus ordering by slug.

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 meters') and immediately qualifies the scenario ('when the exact slug is unknown'). It contrasts itself against list_meters, so an agent can distinguish it from siblings 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?

Explicitly frames the condition for use (slug unknown, non-semantic intent) and names the alternative for the opposing case ('Use list_meters to browse all meters'). When-to-use and the alternative are both stated.

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