Periodic Table 2026

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered without help. The description adds a small amount of output context (values are numeric and carry units) but says nothing about the shape of the comparison, whether missing properties are omitted or nulled, or how units are chosen.

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?

Nine words, front-loaded with the comparison and ending with the constraint most likely to cause an error (units). It wastes nothing, though the fragment construction leaves the central action implicit rather than stated.

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 3 fully described parameters and read-only annotations, the essentials are covered, but there is no output schema and the description does not explain what the comparison returns (per-property rows vs. per-element blocks) or how missing properties are handled. For a tool whose entire value is the result format, that is a real 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 description coverage is 100%, so all three parameters (locale, elements, properties) are already documented inline, including accepted element formats and the enum of properties; baseline 3 applies. The description adds only the "2-10 elements" bound already encoded in minItems/maxItems and the "numeric" hint about the default property set, nothing new.

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?

"Side-by-side numeric properties of 2-10 elements, with units" names the resource (elements), the operation (side-by-side comparison) and a hard scope limit (2-10), which separates it from get_element/list_elements/search_elements without opening a schema. It is a fragment rather than a full verb phrase and never names the siblings explicitly, so it stops short of a 5.

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 when-to-use statement and no mention of the alternatives (get_element for a single element, search_elements for discovery). The comparison intent is merely implied by "side-by-side"; an agent must infer from the name and the 2-10 bound that this is the multi-element path.

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 adds real value by disclosing the breadth and shape of the payload (units on properties, long-form introduction with uses/production/history/safety, external page link), which tells an agent how much context it will get. Missing only failure behavior for unknown elements.

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 dense sentence with the resource stated first and the payload contents listed after. The long parenthetical list is information-dense rather than padded, though it reads as an enumeration rather than guidance.

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 carries the burden of explaining return values and does so thoroughly, covering every major data category. The remaining gap is input behavior (identifier formats, locale fallback), which the schema largely handles.

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 both parameters (flexible element identifier and locale enum) are already documented as well as possible in the schema. The description adds nothing about accepted identifier formats (symbol, atomic number, localized name) or the default locale, so baseline 3 applies.

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 a specific resource ('one element') and enumerates exactly what data is returned (classification, properties with units, electron configuration, discovery, summary, introduction, page link). It's clear this is a single-element detail fetch, but it never explicitly contrasts itself with siblings like search_elements or compare_elements.

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 only implied: 'one element' suggests a detail lookup rather than a list or comparison. There is no statement of when to use this over search_elements (e.g., when the element identifier is already known) or what to do when the element is unknown.

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 adds real behavioral context beyond that: default ordering, the fixed 118-element domain, and the important silent-exclusion rule that elements lacking a value for the range or sort property are dropped from the results.

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, no filler: the first enumerates all filter axes cascade-style, the second carries defaults and the edge case. Front-loaded and appropriately sized for an 11-parameter tool.

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 query tool with 11 all-optional params at full schema coverage, the description covers filter families, default ordering, result-set size, and the null-handling rule. No output schema exists, but a flat element list is implied and nothing needed for correct invocation 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 semantics the schema does not state: min/max and sort interplay with missing values, producing silent omissions. That is a meaningful clarification of parameter behavior rather than restatement.

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 elements) plus scope: all 118 elements in atomic-number order when unfiltered, and the filter axes available. It doesn't name the siblings (get_element, search_elements) to draw a boundary, but the tool's identity is unambiguous.

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?

"Without filters it lists all 118 elements in atomic-number order" clearly establishes the default behavior and the filtered path, so an agent knows when this is the right call. It stops short of explicit routing guidance such as when to prefer search_elements, so it's clear context without 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 readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine value by revealing fuzzy/multilingual matching tolerance, but says nothing about result ordering, relevance ranking, or whether multiple matches are returned.

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, no filler, with the capability statement front-loaded and the selection trigger immediately after. Nothing restates 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?

For a 3-parameter read-only search tool with a fully documented schema and no output schema, the description gives enough to invoke it correctly. Minor gaps are the absence of result-count/ranking expectations and no sibling routing guidance.

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%, with per-parameter examples for query, defaults and bounds for limit, and an enum for locale — so the baseline is 3. The description echoes the query dimensions (symbol, atomic number, name) and 'any supported language' hints at locale, but adds no syntax 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 (find/search) and resource (elements) plus the exact query dimensions: symbol, atomic number, full or partial name. It does not name siblings like get_element or list_elements, so the distinction is inferable but not 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?

'Use it when a name is misspelled, partial or in another language' gives a concrete trigger condition for selection. It stops short of stating when not to use it (e.g. exact lookup should go to get_element) or naming alternatives, so it misses the top band.

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