Digital Gemology: gemology glossary and grading report terms

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description adds real value by disclosing the response contents (short definition, more detail, report location, measurement method, related terms, page) – important since there is no output schema. It omits failure behavior when a term is unknown.

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 no filler; the long parenthetical example list is useful but pushes the payload-heavy content toward the end. Minor trimming of six examples would tighten it without losing meaning.

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 simple read-only parameter and no output schema, the description does the essential job of describing return values. It leaves open what happens for an unknown or misspelled term and when to prefer search_glossary, which matters given the sibling set.

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?

There is one parameter at 100% schema coverage, and the schema already explains that it accepts a term, abbreviation, or alternate name. The description's example terms ('crown angle', 'feather', 'fluorescence') add some concrete guidance on the vocabulary accepted, but no format or matching rules.

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 (a single gemology term) and enumerates concretely what a definition contains, so an agent knows exactly what comes back. It never states the verb/scope relative to siblings (list_glossary, search_glossary), so it does not differentiate itself from them explicitly.

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: the description repeatedly says 'one gemology term', which suggests exact single-term lookup rather than listing or searching. It never names search_glossary as the alternative for fuzzy or partial matches, and gives no exclusions or preconditions.

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, non-destructive and closed-world, so safety is covered. The description earns credit for disclosing the return shape — a one-line definition and its page per term — which matters because there is no output schema, and for making clear the filter is optional ('all if left out' is mirrored in the 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?

The opening sentence is well front-loaded and does real work. The second sentence is a verbatim duplication of the enum already present in the schema and consumes most of the description's length, which crowds out the more valuable missing content (when to use this versus the two siblings).

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 zero-required-param, single-filter read tool with rich annotations and no output schema, the description covers scope and return content adequately. The only real gap is routing guidance against define_term and search_glossary, which is a modest rather than fatal omission.

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% and the single parameter is a fully enumerated enum, so the schema already does all the work. The description's second sentence simply re-lists the same 15 enum values, adding no meaning about defaults or behavior beyond what the schema shows.

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 resource (the glossary) and scope (all terms or one topic) and states what comes back (one-line definition plus page). It is clear what the tool does, though it never names or contrasts with search_glossary or define_term, so an agent must infer the boundary itself.

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: 'Every term ... or in one topic' suggests browsing rather than targeted lookup, and the topic list hints at the taxonomy. It never says when to prefer this over search_glossary (keyword search) or define_term (single definition), which is the one decision an agent actually has to make.

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 read-only, idempotent, non-destructive behavior, so the description earns credit mainly for disclosing the return shape ('each match with its definition and page'), which matters since there is no output schema. It says nothing about ranking, match quality, or what happens on zero 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?

One front-loaded sentence plus a short return statement, no waste. The three inline example queries are illustrative rather than filler, though they add length without covering the optional filters.

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 three-parameter read-only search with no output schema, the description covers what it does, what inputs look like, and what comes back. Only the interaction between query and the topic filter is left unaddressed.

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% with all three parameters documented, so the baseline is 3. The description does add that 'query' accepts natural-language questions, mildly extending the schema's 'A word, a few words or a question', but says nothing about 'topic' or 'limit'.

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 glossary terms') and clarifies the input can be a word or a full question. It distinguishes itself implicitly from define_term/list_glossary by framing the operation as search over many terms, but never names those siblings.

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 parenthetical examples strongly imply when this tool fits (fuzzy, conceptual, or question-shaped lookups), but there is no explicit statement of when to prefer define_term for a known term or list_glossary for browsing.

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