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

No annotations are supplied, so the description must carry the full disclosure burden and it largely does not: it never states that this is a read-only lookup, what happens if code is ambiguous and table is omitted (error vs. best guess), or what the explanation output contains. The only behavioral hint is the ambiguous-code/table dependency, which is minimal for a zero-annotation tool.

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 short sentence with the usage condition front-loaded and no filler. The terseness is efficient, though it borders on under-specification rather than tight writing.

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 0% schema coverage, no annotations, and no output schema, this definition should explain the domain concepts (source rules, outcomes) and the code/table relationship. It leaves the agent without enough to invoke confidently – notably what an explanation looks like and where table IDs come from.

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 0%, so the schema contributes no meaning for code or table. The description does add one genuinely useful semantic – table is needed specifically when code is ambiguous – but it never says what form a code or table ID takes or how to obtain a valid table ID.

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?

"Explain source rules and outcomes" gives a verb and a rough object, but the terms "source rules" and "outcomes" are domain jargon that never tie back to the tool name explain_position. None of the siblings (import_positions, filter_positions, search_majors) are referenced, so the agent must guess what distinguishes this from filter_positions or search_majors.

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 clause "ambiguous codes require a table ID" is a conditional invocation rule, but it is about parameter preconditions rather than when to pick this tool over siblings. There is no statement of when to use it (e.g., after import_positions, or when filter_positions returns an unexpected result) and no 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?

With no annotations provided, the description carries the full behavioral burden. It discloses conservative screening and manual review for unknown clauses, which is useful context, but omits whether the operation is read-only, what happens to filtered items, permissions, side effects, and any rate or safety constraints.

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 single sentence is compact but severely under-specified rather than genuinely concise. It front-loads an action but leaves the resource and operational context unclear.

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?

The presence of an output schema means return values need not be explained, but the description still fails to cover the two optional object parameters and the tool's filtering behavior. For a tool with no annotations and vague input schema, more context is 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?

The schema has 0% description coverage and the description never mentions the two parameters, filters and profile. It adds no meaning about their expected shape or purpose beyond the bare schema titles.

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 says "Screen parsed conditions conservatively" but never identifies the resource being filtered (positions) or what kinds of conditions are screened. It does not clearly distinguish the tool from siblings such as explain_position, import_positions, or search_majors.

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?

It states a rule for unknown clauses requiring manual review, but gives no guidance on when to use this tool instead of the sibling tools. There is no context about prerequisites, expected inputs, or alternative workflows.

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?

With no annotations, the description carries the full behavioral burden. It usefully discloses that the operation writes SQLite and that identical imports are skipped, but it omits overwrite/merge semantics, what counts as identical, permission requirements, and failure 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?

The description is two short, front-loaded sentences with no wasted wording. Its terseness is efficient, though it also contributes to the missing behavioral and parameter detail.

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 four-parameter mutation tool with no annotations, no output schema, and 0% schema description coverage, this is significantly underspecified. An agent would not know the expected file format, mapping semantics, or import side effects beyond the bare fact that SQLite is written.

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 0% across four parameters, so the description must compensate but does not. It never explains what path refers to, how year is used, what the mapping values mean, or what announcement does.

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 states a specific action and resource: importing a local user-supplied table into SQLite. It is clear that this is a write/import operation, which contrasts with the read-oriented sibling tools, though it does not explicitly name 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?

There is no guidance on when this tool should be used instead of the query/filter/explain siblings, nor are prerequisites or supported import scenarios described. The only usage-adjacent information is that identical imports are skipped.

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?

No annotations are supplied, so the description carries the full behavioral burden. It does disclose one useful trait — that the query runs against a local catalogue with no network request — but says nothing about read-only nature, failure behavior on unmatched keywords, or result scoping; the output schema covers return shape.

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 short sentence with no filler, and the local-execution note is front-loaded. Brevity here is efficient rather than padded, though it crosses into under-specification rather than crispness.

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?

The tool is structurally simple (one required parameter, output schema present), so the bar is low and returns need not be explained. Still, the description leaves the core subject matter and the keyword's matching behavior unexplained, which is insufficient even for a simple search.

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 0% and the single required parameter "keyword" is completely undocumented in both schema and description. The description adds no matching semantics (substring vs exact, case sensitivity, empty-string handling) that an agent would need to call it correctly.

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?

"Search" merely restates the verb already in the name, and the resource is described only as a "local replaceable catalogue subset", which is cryptic jargon. Nothing in the description explains what a "major" is or how this differs from the position-oriented siblings (filter_positions, explain_position).

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 statement of when to use this tool versus filter_positions or explain_position, despite obvious overlap with a filtering tool. The only hint is "no network request", which implies an offline path but gives no routing rule or prerequisites.

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